Search Results (62)

Leaf loss caused by pest infestations poses a serious threat to forest health. The leaf loss rate (LLR) refers to the percentage of the overall tree-crown leaf loss per unit area and is an important indicator for evaluating forest health. Therefore, rapid and accurate acquisition of the LLR via remote sensing monitoring is crucial. This study is based on drone hyperspectral and LiDAR data as well as ground survey data, calculating hyperspectral indices (HSI), multispectral indices (MSI), and LiDAR indices (LI). It employs Savitzky–Golay (S–G) smoothing with different window sizes (W) and polynomial orders (P) combined with recursive feature elimination (RFE) to select sensitive features. Using Random Forest Regression (RFR) and Convolutional Neural Network Regression (CNNR) to construct a multidimensional (horizontal and vertical) estimation model for LLR, combined with LiDAR point cloud data, achieved a three-dimensional visualization of the leaf loss rate of trees. The results of the study showed: (1) The optimal combination of HSI and MSI was determined to be W11P3, and the LI was W5P2. (2) The optimal combination of the number of sensitive features extracted by the RFE algorithm was 13 HSI, 16 MSI, and hierarchical LI (2 in layer I, 9 in layer II, and 11 in layer III). (3) In terms of the horizontal estimation of the defoliation rate, the model performance index of the CNNR_HSI model (MPI = 0.9383) was significantly better than that of RFR_MSI (MPI = 0.8817), indicating that the continuous bands of hyperspectral could better monitor the subtle changes of LLR. (4) The I-CNNR_HSI+LI, II-CNNR_HSI+LI, and III-CNNR_HSI+LI vertical estimation models were constructed by combining the CNNR_HSI model with the best accuracy and the LI sensitive to different vertical levels, respectively, and their MPIs reached more than 0.8, indicating that the LLR estimation of different vertical levels had high accuracy. According to the model, the pixel-level LLR of the sample tree was estimated, and the three-dimensional display of the LLR for forest trees under the pest stress of larch caterpillars was generated, providing a high-precision research scheme for LLR estimation under pest stress. Full article

Structural health monitoring in resource-constrained environments demands crack segmentation models that match the accuracy of heavyweight convolutional networks while conforming to the power, memory, and latency limits of watt-level edge devices. This study presents a lightweight dual-attention network, which is a four-stage U-Net compressed to one-quarter of the channel depth and augmented—exclusively at the deepest layer—with a compact dual-attention block that couples channel excitation with spatial self-attention. The added mechanism increases computation by only 19%, limits the weight budget to 7.4 MB, and remains fully compatible with post-training INT8 quantization. On a pixel-labelled concrete crack benchmark, the proposed network achieves an intersection over union of 0.827 and an F1 score of 0.905, thus outperforming CrackTree, Hybrid 2020, MobileNetV3, and ESPNetv2. While refined weight initialization and Dice-augmented loss provide slight improvements, ablation experiments show that the dual-attention module is the main factor influencing accuracy. With 110 frames per second on a 10 W Jetson Nano and 220 frames per second on a 5 W Coral TPU achieved without observable accuracy loss, hardware-in-the-loop tests validate real-time viability. Thus, the proposed network offers cutting-edge crack segmentation at the kiloflop scale, thus facilitating ongoing, on-device civil infrastructure inspection. Full article

Cracks and dents in concrete structures are core defects that threaten building safety, but the existing YOLO series algorithms face a huge bottleneck in complex engineering scenarios. Tiny cracks are susceptible to background texture interference, leading to misjudgment. The traditional detection frame has difficulty in accurately characterizing the dent geometry, which affects the quantitative damage assessment. In this paper, we propose a Multi-level Defect Fusion Segmentation Network (MDFNet) to break through the single-task limitation through the detection segmentation synergy framework. We improve the anchor frame strategy of YOLOv11 and enhance the recall of small targets by combining Copy–Pasting, and then enhance the pixel-level characterization of crack edges and dent contours by embedding the Head Attention-Expanded Convolutional Fusion Module (HAEConv) in U-Net with squeeze-and-excitation (SE) channel attention. Joint detection loss and segmentation loss are used for task co-optimization. On our self-constructed concrete defect dataset, MDFNet significantly outperforms the baseline model. In terms of accuracy, the MDFNet Dice coefficient is 92.4%, an improvement of 4.1 percentage points compared to YOLOv11-Seg. Our mean Intersection over Union (mIoU) reaches 81.6%, with strong generalization ability under complex background interference. In terms of engineering efficacy, the model achieves a processing speed of 45 frames per second (FPS) for 640 × 640 images, which is able to meet real-time monitoring requirements. The experimental results verify the feasibility of the model in the research field of crack and dent detection in concrete structures. Full article

Event-based cameras, inspired by biological vision, asynchronously capture per-pixel brightness changes, producing streams of events with higher temporal resolution, dynamic range, and lower latency than conventional cameras. These advantages make event cameras promising for human pose estimation in challenging scenarios, such as motion blur and low-light conditions. However, human pose estimation with event cameras is still in its early research stages. Among major challenges is information loss from stationary parts of the human body, where the stationary parts at instances cannot trigger events. This issue, inherent to the nature of event data, cannot be resolved in a short-range event stream alone. Therefore, incorporating motion cues from a longer temporal range offers a intuitive solution. This paper proposes a joint global and local temporal modeling network (JGLTM), designed to extract essential cues from a longer temporal range to complement and refine local features for more accurate current pose prediction. Unlike existing methods that rely only on short-range temporal correspondence, this approach expands the temporal perception field to effectively provide crucial contexts for the lost information of stationary body parts at the current time instance. Extensive experiments on public datasets and the dataset proposed in this paper demonstrate the effectiveness and superiority of the proposed approach in event-based human pose estimation across diverse scenarios. Full article

Microcrack detection using deep neural networks (DNNs) through an automated pipeline using wave fields interacting with the damaged areas is highly sought after. However, these high-dimensional spatio–temporal crack data are limited. Moreover, these datasets have large dimensions in the temporal domain. The dataset presents a substantial class imbalance, with crack pixels constituting an average of only 5% of the total pixels per sample. This extreme class imbalance poses a challenge for deep learning models with different microscale cracks, as the network can be biased toward predicting the majority class, generally leading to poor detection accuracy for the under-represented class. This study proposes an asymmetric encoder–decoder network with an adaptive feature reuse block for microcrack detection. The impact of various activation and loss functions are examined through feature space visualisation using the manifold discovery and analysis (MDA) algorithm. The optimized architecture and training methodology achieved an accuracy of 87.74%. Full article

Micro-size light-emitting diodes (μLEDs) are high-brightness, low-power optoelectronic devices with significant potential in display technology, lighting, and biomedical applications. AlGaInP-based red LEDs experience severe size-dependent effects when scaled to the micron level, and addressing the fabrication challenges of GaN-based red μLED arrays is crucial for achieving homogeneous integration. This study investigates the employment of KOH wet treatments to alleviate efficiency degradation caused by sidewall leakage currents. GaN-based red μLED arrays with pixel sizes ranging from 5 × 5 µm² to 20 × 20 µm² were grown using metal-organic chemical vapor deposition (MOCVD), and then fabricated via rapid thermal annealing, mesa etching, sidewall wet treatment, electrode deposition, sidewall passivation, chemical-mechanical polishing, and via processes. The arrays, with pixel densities ranging from 668 PPI (Pixel Per Inch) to 1336 PPI, consist of 10,000 to 40,000 emitting pixels, and their optoelectronic properties were systematically evaluated. The arrays with varying pixel sizes fabricated in this study were subjected to three distinct processing conditions: without KOH treatment, 3 min of KOH treatment, and 5 min of KOH treatment. Electrical characterization reveals that the 5-min KOH treatment significantly reduces leakage current, enhancing the electrical performance, as compared to the samples without KOH treatment or 3-min treatment. In terms of optical properties, while the arrays without any KOH treatment failed to emit light, the ones with 3- and 5-min KOH treatment exhibit excellent optical uniformity and negligible blue shift. Most arrays treated for 5 min demonstrate superior light output power (LOP) and optoelectronic efficiency, with the 5 µm pixel arrays exhibiting unexpectedly high performance. The results suggest that extending the KOH wet treatment time effectively mitigates sidewall defects, reduces non-radiative recombination, and enhances surface roughness, thereby minimizing optical losses. These findings provide valuable insights for optimizing the fabrication of high-performance GaN-based red μLEDs and contribute to the development of stable, high-quality small-pixel μLEDs for advanced display and lighting applications. Full article

Augmented reality applications involving human interaction with virtual objects often rely on segmentation-based hand detection techniques. Semantic segmentation can then be enhanced with instance-specific information to model complex interactions between objects, but extracting such information typically increases the computational load significantly. This study proposes a training strategy that enables conventional semantic segmentation networks to preserve some instance information during inference. This is accomplished by introducing pixel weight maps into the loss calculation, increasing the importance of boundary pixels between instances. We compare two common fully convolutional network (FCN) architectures, U-Net and ResNet, and fine-tune the fittest to improve segmentation results. Although the resulting model does not reach state-of-the-art segmentation performance on the EgoHands dataset, it preserves some instance information with no computational overhead. As expected, degraded segmentations are a necessary trade-off to preserve boundaries when instances are close together. This strategy allows approximating instance segmentation in real-time using non-specialized hardware, obtaining a unique blob for an instance with an intersection over union greater than 50% in 79% of the instances in our test set. A simple FCN, typically used for semantic segmentation, has shown promising instance segmentation results by introducing per-pixel weight maps during training for light-weight applications. Full article

Underwater object detection is highly complex and requires a high speed and accuracy. In this paper, an underwater target detection model based on YOLOv8 (SPSM-YOLOv8) is proposed. It solves the problems of high computational complexities, slow detection speeds and low accuracies. Firstly, the SPDConv module is utilized in the backbone network to replace the standard convolutional module for feature extraction. This enhances computational efficiency and reduces redundant computations. Secondly, the PSA (Polarized Self-Attention) mechanism is added to filter and enhance the polarization of features in the channel and spatial dimensions to improve the accuracy of pixel-level prediction. The SCDown (spatial–channel decoupled downsampling) downsampling mechanism is then introduced to reduce the computational cost by decoupling the space and channel operations while retaining the information in the downsampling process. Finally, MPDIoU (Minimum Point Distance-based IoU) is used to replace the CIoU (Complete-IOU) loss function to accelerate the convergence speed of the bounding box and improve the bounding box regression accuracy. The experimental results show that compared with the YOLOv8n baseline model, the SPSM-YOLOv8 (SPDConv-PSA-SCDown-MPDIoU-YOLOv8) detection accuracy reaches 87.3% on the ROUD dataset and 76.4% on the UPRC2020 dataset, and the number of parameters and amount of computation decrease by 4.3% and 4.9%, respectively. The detection frame rate reaches 189 frames per second on the ROUD dataset, thus meeting the high accuracy requirements for underwater object detection algorithms and facilitating lightweight and fast edge deployment. Full article

In view of the low levels of speed and precision associated with fault detection in transmission lines using traditional algorithms due to resource constraints, a transmission line fault target-detection method for YOLOv8 (You Only Look Once version 8) based on the Rep (Representational Pyramid) Visual Transformer and incorporating an ultra-lightweight module is proposed. First, the YOLOv8 detection network was built. In order to address the needs of feature redundancy and high levels of network computation, the Rep Visual Transformer module was introduced in the Neck part to integrate the pixel information associated with the entire image through its multi-head self-attention and enable the model to learn more global image features, thereby improving the computational speed of the model; then, a lightweight GSConv (Grouped and Separated Convolution, a combination of grouped convolution and separated convolution) convolution module was added to the Backbone and Neck to share computing resources among channels and reduce computing time and memory consumption, by which the computational cost and detection performance of the detection network were balanced, while the model remained lightweight and maintained its high precision. Secondly, the loss function Wise-IoU (Intelligent IOU) was introduced as the Bounding-Box Regression (BBR) loss function to optimize the predicted bounding boxes in these grid cells and shift them closer to the real target location, which reduced the harmful gradients caused by low-quality examples and further improved the detection precision of the algorithm. Finally, the algorithm was verified using a data set of 3500 images compiled by a power-supply inspection department over the past four years. The experimental results show that, compared with the seven classic and improved algorithms, the recall rate and average precision of the proposed algorithm were improved by 0.058 and 0.053, respectively, compared with the original YOLOv8 detection network; the floating-point operations per second decreased by 2.3; and the picture detection speed was increased to 114.9 FPS. Full article

Ship detection faces significant challenges such as dense arrangements, varying dimensions, and interference from the sea surface background. Existing ship detection methods often fail to accurately identify ships in these complex marine environments. This paper presents OptiShipNet, an efficient network for detecting ships in complex marine environments using optical remote sensing images. First, to effectively capture ship features from complex environments, we designed a DFC-ConvNeXt module as the network’s backbone, where decoupled fully connected (DFC) attention captures long-distance information in both vertical and horizontal directions, thereby enhancing its expressive capabilities. Moreover, a simple, parameter-free attention module (SimAM) is integrated into the network’s neck to enhance focus on ships within challenging backgrounds. To achieve precise ship localization, we employ WIoU loss, enhancing the ship positioning accuracy in complex environments. Acknowledging the lack of suitable datasets for intricate backgrounds, we construct the HRSC-CB dataset, featuring high-resolution optical remote sensing images. This dataset contains 3786 images, each measuring 1000 × 600 pixels. Experiments demonstrate that the proposed model accurately detects ships under complex scenes, achieving an average precision (AP) of 94.1%, a 3.2% improvement over YOLOv5. Furthermore, the model’s frame per second (FPS) rate reaches 80.35, compared to 67.84 for YOLOv5, thus verifying the approach’s effectiveness. Full article

Real-time automatic detection of microcracks in eggs is crucial for ensuring egg quality and safety, yet rapid detection of micron-scale cracks remains challenging. This study introduces a real-time ConvNext-Based U-Net model with Feature Infusion (CBU-FI Net) for egg microcrack detection. Leveraging edge features and spatial continuity of cracks, we incorporate an edge feature infusion module in the encoder and design a multi-scale feature aggregation strategy in the decoder to enhance the extraction of both local details and global semantic information. By introducing large convolution kernels and depth-wise separable convolution from ConvNext, the model significantly reduces network parameters compared to the original U-Net. Additionally, a composite loss function is devised to address class imbalance issues. Experimental results on a dataset comprising over 3400 graded egg microcrack image patches demonstrate that CBU-FI Net achieves a reduction in parameters to one-third the amount in the original U-Net, with an inference speed of 21 ms per image (1 million pixels). The model achieves a Crack-IoU of 65.51% for microcracks smaller than 20 $\mathsf{\mu }$m and a Crack-IoU and MIoU of 60.76% and 80.22%, respectively, for even smaller cracks (less than 5 $\mathsf{\mu }$m), achieving high-precision, real-time detection of egg microcracks. Furthermore, on the publicly benchmarked CrackSeg9k dataset, CBU-FI Net achieves an inference speed of 4 ms for 400 × 400 resolution images, with an MIoU of 81.38%, proving the proposed method’s robustness and generalization capability across various cracks and complex backgrounds. Full article

Fruit is a major source of vitamins, minerals, and dietary fiber in people’s daily lives. Leaf diseases caused by climate change and other factors have significantly reduced fruit production. Deep learning methods for segmenting leaf diseases can effectively mitigate this issue. However, challenges such as leaf folding, jaggedness, and light shading make edge feature extraction difficult, affecting segmentation accuracy. To address these problems, this paper proposes a method based on EFS-Former. The expanded local detail (ELD) module extends the model’s receptive field by expanding the convolution, better handling fine spots and effectively reducing information loss. H-attention reduces computational redundancy by superimposing multi-layer convolutions, significantly improving feature filtering. The parallel fusion architecture effectively utilizes the different feature extraction intervals of the convolutional neural network (CNN) and Transformer encoders, achieving comprehensive feature extraction and effectively fusing detailed and semantic information in the channel and spatial dimensions within the feature fusion module (FFM). Experiments show that, compared to DeepLabV3+, this method achieves 10.78%, 9.51%, 0.72%, and 8.00% higher scores for mean intersection over union (mIoU), mean pixel accuracy (mPA), accuracy (Acc), and F_score, respectively, while having 1.78 M fewer total parameters and 0.32 G lower floating point operations per second (FLOPS). Additionally, it effectively calculates the ratio of leaf area occupied by spots. This method is also effective in calculating the disease period by analyzing the ratio of leaf area occupied by diseased spots. The method’s overall performance is evaluated using mIoU, mPA, Acc, and F_score metrics, achieving 88.60%, 93.49%, 98.60%, and 95.90%, respectively. In summary, this study offers an efficient and accurate method for fruit tree leaf spot segmentation, providing a solid foundation for the precise analysis of fruit tree leaves and spots, and supporting smart agriculture for precision pesticide spraying. Full article

Coastal wetlands are vulnerable to accelerated sea-level rise, yet knowledge about their extent and distribution is often limited. We developed a land cover classification of wetlands in the coastal plains of the southern United States along the Gulf of Mexico (Texas, Louisiana, Mississippi, Alabama, and Florida) using 6161 very-high (2 m per pixel) resolution WorldView-2 and WorldView-3 satellite images from 2012 to 2015. Area extent estimations were obtained for the following vegetated classes: marsh, scrub, grass, forested upland, and forested wetland, located in elevation brackets between 0 and 10 m above sea level at 0.1 m intervals. Sea-level trends were estimated for each coastal state using tide gauge data collected over the period 1983–2021 and projected for 2100 using the trend estimated over that period. These trends were considered conservative, as sea level rise in the region accelerated between 2010 and 2021. Estimated losses in vegetation area due to sea level rise by 2100 are projected to be at least 12,587 km², of which 3224 km² would be coastal wetlands. Louisiana is expected to suffer the largest losses in vegetation (80%) and coastal wetlands (75%) by 2100. Such high-resolution coastal mapping products help to guide adaptation plans in the region, including planning for wetland conservation and coastal development. Full article

Automatic Container Code Recognition (ACCR) is critical for enhancing the efficiency of container terminals. However, existing ACCR methods frequently fail to achieve satisfactory performance in complex environments at port gates. In this paper, we propose an approach for accurate, fast, and compact container code recognition by utilizing YOLOv4 for container region localization and Deeplabv3+ for character recognition. To enhance the recognition speed and accuracy of YOLOv4 and Deeplabv3+, and to facilitate their deployment at gate entrances, we introduce several improvements. First, we optimize the feature-extraction process of YOLOv4 and Deeplabv3+ to reduce their computational complexity. Second, we enhance the multi-scale recognition and loss functions of YOLOv4 to improve the accuracy and speed of container region localization. Furthermore, we adjust the dilated convolution rates of the ASPP module in Deeplabv3+. Finally, we replace two upsampling structures in the decoder of Deeplabv3+ with transposed convolution upsampling and sub-pixel convolution upsampling. Experimental results on our custom dataset demonstrate that our proposed method, C-YOLOv4, achieves a container region localization accuracy of 99.76% at a speed of 56.7 frames per second (FPS), while C-Deeplabv3+ achieves an average pixel classification accuracy (MPA) of 99.88% and an FPS of 11.4. The overall recognition success rate and recognition speed of our approach are 99.51% and 2.3 ms per frame, respectively. Moreover, C-YOLOv4 and C-Deeplabv3+ outperform existing methods in complex scenarios. Full article

Tea plants (Camellia sinensis (L.) Kuntze) are a cash crop that thrive under warm and moist conditions. However, tea plants are becoming increasingly vulnerable to heat damage (HD) during summer growing seasons due to global climate warming. Because China ranks first in the world in both harvested tea area and total tea production, monitoring and tracking HD to tea plants in a timely manner has become a significant and urgent task for scientists and tea producers in China. In this study, the spatiotemporal characteristics of HD evolution were analyzed, and a tracking method using HD LST-weighted geographical centroids was constructed based on HD pixels identified by the critical LST threshold and daytime MYD11A1 products over the major tea planting regions of mainland China from two typical HD years (2013 and 2022). Results showed that the average number of HD days in 2022 was five more than in 2013. Daily HD extent increased at a rate of 0.66% per day in 2022, which was faster than that in 2013 with a rate of 0.21% per day. In two typical HD years, the tea regions with the greatest HD extent were concentrated south of the Yangtze River (SYR), with average HD pixel ratios of greater than 50%, then north of the Yangtze River (NYR) and southwest China (SWC), with average HD pixel ratios of around 40%. The regions with the least HD extent were in South China (SC), where the HD ratios were less than 40%. The HD LST-weighted geographical centroid trajectories showed that HD to tea plants in 2013 initially moved from southwest to northeast, and then moved west. In 2022, HD moved from northeast to west and south. Daily HD centroids were mainly concentrated at the conjunction of SYR, SWC, and SC in 2013, and in northern SWC in 2022, where they were near to the centroid of the tea planting gardens. The findings in this study confirmed that monitoring HD evolution of tea plants over a large spatial extent based on reconstructed remotely sensed LST values and critical threshold was an effective method benefiting from available MODIS LST products. Moreover, this method can identify and track the spatial distribution characteristics of HD to tea plants in a timely manner, and it will therefore be helpful for taking effective preventative measures to mitigate economic losses resulting from HD. Full article