Search Results (250)

Visual recognition and localization of underwater optical beacons are critical for AUV docking, but traditional beacons are limited by fixed directionality and light attenuation in water. To extend the range of optical docking, this study designs a novel omnidirectional rotating optical beacon that provides 360-degree light coverage over 45 m, improving beacon detection probability through synchronized scanning. Addressing the challenges of light centroid detection, we introduce a parallel deep learning detection algorithm based on an improved YOLOv8-pose model. Initially, an underwater optical beacon dataset encompassing various light patterns was constructed. Subsequently, the network was optimized by incorporating a small detection head, implementing dynamic convolution and receptive-field attention convolution for single-stage multi-scale localization. A post-processing method based on keypoint joint IoU matching was proposed to filter redundant detections. The algorithm achieved 93.9% AP at 36.5 FPS, with at least a 5.8% increase in detection accuracy over existing methods. Moreover, a light-source-based measurement method was developed to accurately detect the beacon’s orientation. Experimental results indicate that this scheme can achieve high-precision omnidirectional guidance with azimuth and pose estimation errors of -4.54° and 3.09°, respectively, providing a reliable solution for long-range and large-scale optical docking. Full article

The precise extraction of building footprints using remote sensing technology is increasingly critical for urban planning and development amid growing urbanization. However, considering the complexity of building backgrounds, diverse scales, and varied appearances, accurately and efficiently extracting building footprints from various remote sensing images remains a significant challenge. In this paper, we propose a novel network architecture called ME-FCN, specifically designed to perceive and optimize multi-scale features to effectively address the challenge of extracting building footprints from complex remote sensing images. We introduce a Squeeze-and-Excitation U-Block (SEUB), which cascades multi-scale semantic information exploration in shallow feature maps and incorporates channel attention to optimize features. In the network’s deeper layers, we implement an Adaptive Multi-scale feature Enhancement Block (AMEB), which captures large receptive field information through concatenated atrous convolutions. Additionally, we develop a novel Dual Multi-scale Attention (DMSA) mechanism to further enhance the accuracy of cascaded features. DMSA captures multi-scale semantic features across both channel and spatial dimensions, suppresses redundant information, and realizes multi-scale feature interaction and fusion, thereby improving the overall accuracy and efficiency. Comprehensive experiments on three datasets demonstrate that ME-FCN outperforms mainstream segmentation methods. Full article

Photovoltaic panel defect detection presents significant challenges due to the wide range of defect scales, diverse defect types, and severe background interference, often leading to a high rate of false positives and missed detections. To address these challenges, this paper proposes the LEM-Detector, an efficient end-to-end photovoltaic panel defect detector based on the transformer architecture. To address the low detection accuracy for Crack and Star crack defects and the imbalanced dataset, a novel data augmentation method, the Linear Feature Augmentation (LFA) module, specifically designed for linear features, is introduced. LFA effectively improves model training performance and robustness. Furthermore, the Efficient Feature Enhancement Module (EFEM) is presented to enhance the receptive field, suppress redundant information, and emphasize meaningful features. To handle defects of varying scales, complementary semantic information from different feature layers is leveraged for enhanced feature fusion. A Multi-Scale Multi-Feature Pyramid Network (MMFPN) is employed to selectively aggregate boundary and category information, thereby improving the accuracy of multi-scale target recognition. Experimental results on a large-scale photovoltaic panel dataset demonstrate that the LEM-Detector achieves a detection accuracy of 94.7% for multi-scale defects, outperforming several state-of-the-art methods. This approach effectively addresses the challenges of photovoltaic panel defect detection, paving the way for more reliable and accurate defect identification systems. This research will contribute to the automatic detection of surface defects in industrial production, ultimately enhancing production efficiency. Full article

Text CAPTCHAs are crucial security measures deployed on global websites to deter unauthorized intrusions. The presence of anti-attack features incorporated into text CAPTCHAs limits the effectiveness of evaluating them, despite CAPTCHA recognition being an effective method for assessing their security. This study introduces a novel color augmentation technique called Variational Color Shift (VCS) to boost the recognition accuracy of different networks. VCS generates a color shift of every input image and then resamples the image within that range to generate a new image, thus expanding the number of samples of the original dataset to improve training effectiveness. In contrast to Random Color Shift (RCS), which treats the color offsets as hyperparameters, VCS estimates color shifts by reparametrizing the points sampled from the uniform distribution using predicted offsets according to every image, which makes the color shifts learnable. To better balance the computation and performance, we also propose two variants of VCS: Sim-VCS and Dilated-VCS. In addition, to solve the overfitting problem caused by disturbances in text CAPTCHAs, we propose an Auto-Encoder (AE) based on Large Separable Kernel Attention (AE-LSKA) to replace the convolutional module with large kernels in the text CAPTCHA recognizer. This new module employs an AE to compress the interference while expanding the receptive field using Large Separable Kernel Attention (LSKA), reducing the impact of local interference on the model training and improving the overall perception of characters. The experimental results show that the recognition accuracy of the model after integrating the AE-LSKA module is improved by at least 15 percentage points on both M-CAPTCHA and P-CAPTCHA datasets. In addition, experimental results demonstrate that color augmentation using VCS is more effective in enhancing recognition, which has higher accuracy compared to RCS and PCA Color Shift (PCA-CS). Full article

Due to the complexity and diversity of underwater environments, traditional object detection algorithms face challenges in maintaining robustness and detection accuracy when applied underwater. This paper proposes an underwater object detection algorithm based on an improved YOLOv8 model. First, the introduction of CIB building blocks into the backbone network, along with the optimization of the C2f structure and the incorporation of large-kernel depthwise convolutions, effectively enhances the model’s receptive field. This improvement increases the capability of detecting multi-scale objects in complex underwater environments without adding a computational burden. Next, the incorporation of a Partial Self-Attention (PSA) module at the end of the backbone network enhances model efficiency and optimizes the utilization of computational resources while maintaining high performance. Finally, the integration of the Neck component from the Gold-YOLO model improves the neck structure of the YOLOv8 model, facilitating the fusion and distribution of information across different levels, thereby achieving more efficient information integration and interaction. Experimental results show that YOLOv8-CPG significantly outperforms the traditional YOLOv8 in underwater environments. Precision and Recall show improvements of 2.76% and 2.06%. Additionally, mAP50 and mAP50-95 metrics have increased by 1.05% and 3.55%, respectively. Our approach provides an efficient solution to the difficulties encountered in underwater object detection. Full article

In recent years, research on Unmanned Aerial Vehicles (UAVs) has developed rapidly. Compared to traditional remote-sensing images, UAV images exhibit complex backgrounds, high resolution, and large differences in object scales. Therefore, UAV object detection is an essential yet challenging task. This paper proposes a multi-scale object detection network, namely YOLO-DroneMS (You Only Look Once for Drone Multi-Scale Object), for UAV images. Targeting the pivotal connection between the backbone and neck, the Large Separable Kernel Attention (LSKA) mechanism is adopted with the Spatial Pyramid Pooling Factor (SPPF), where weighted processing of multi-scale feature maps is performed to focus more on features. And Attentional Scale Sequence Fusion DySample (ASF-DySample) is introduced to perform attention scale sequence fusion and dynamic upsampling to conserve resources. Then, the faster cross-stage partial network bottleneck with two convolutions (named C2f) in the backbone is optimized using the Inverted Residual Mobile Block and Dilated Reparam Block (iRMB-DRB), which balances the advantages of dynamic global modeling and static local information fusion. This optimization effectively increases the model’s receptive field, enhancing its capability for downstream tasks. By replacing the original CIoU with WIoUv3, the model prioritizes anchoring boxes of superior quality, dynamically adjusting weights to enhance detection performance for small objects. Experimental findings on the VisDrone2019 dataset demonstrate that at an Intersection over Union (IoU) of 0.5, YOLO-DroneMS achieves a 3.6% increase in mAP@50 compared to the YOLOv8n model. Moreover, YOLO-DroneMS exhibits improved detection speed, increasing the number of frames per second (FPS) from 78.7 to 83.3. The enhanced model supports diverse target scales and achieves high recognition rates, making it well-suited for drone-based object detection tasks, particularly in scenarios involving multiple object clusters. Full article

Automatically extracting buildings from remote sensing imagery using deep learning techniques has become essential for various real-world applications. However, mainstream methods often encounter difficulties in accurately extracting and reconstructing fine-grained features due to the heterogeneity and scale variations in building appearances. To address these challenges, we propose LDFormer, an advanced building segmentation model based on linear decay. LDFormer introduces a multi-scale detail fusion bridge (MDFB), which dynamically integrates shallow features to enhance the representation of local details and capture fine-grained local features effectively. To improve global feature extraction, the model incorporates linear decay self-attention (LDSA) and depthwise large separable kernel multi-layer perceptron (DWLSK-MLP) optimizations in the decoder. Specifically, LDSA employs a linear decay matrix within the self-attention mechanism to address long-distance dependency issues, while DWLSK-MLP utilizes step-wise convolutions to achieve a large receptive field. The proposed method has been evaluated on the Massachusetts, Inria, and WHU building datasets, achieving IoU scores of 76.10%, 82.87%, and 91.86%, respectively. LDFormer demonstrates superior performance compared to existing state-of-the-art methods in building segmentation tasks, showcasing its significant potential for building automation extraction. Full article

To address the issues of target feature blurring and increased false detections caused by high compression rates in deepfake videos, as well as the high computational resource requirements of existing face extractors, we propose a lightweight face extractor to assist deepfake detection, GCS-YOLOv8. Firstly, we employ the HGStem module for initial downsampling to address the issue of false detections of small non-face objects in deepfake videos, thereby improving detection accuracy. Secondly, we introduce the C2f-GDConv module to mitigate the low-FLOPs pitfall while reducing the model’s parameters, thereby lightening the network. Additionally, we add a new P6 large target detection layer to expand the receptive field and capture multi-scale features, solving the problem of detecting large-scale faces in low-compression deepfake videos. We also design a cross-scale feature fusion module called CCFG (CNN-based Cross-Scale Feature Fusion with GDConv), which integrates features from different scales to enhance the model’s adaptability to scale variations while reducing network parameters, addressing the high computational resource requirements of traditional face extractors. Furthermore, we improve the detection head by utilizing group normalization and shared convolution, simplifying the process of face detection while maintaining detection performance. The training dataset was also refined by removing low-accuracy and low-resolution labels, which reduced the false detection rate. Experimental results demonstrate that, compared to YOLOv8, this face extractor achieves the AP of 0.942, 0.927, and 0.812 on the WiderFace dataset’s Easy, Medium, and Hard subsets, representing improvements of 1.1%, 1.3%, and 3.7% respectively. The model’s parameters and FLOPs are only 1.68 MB and 3.5 G, reflecting reductions of 44.2% and 56.8%, making it more effective and lightweight in extracting faces from deepfake videos. Full article

Due to the small size of vehicle targets, complex background environments, and the discrete scattering characteristics of high-resolution synthetic aperture radar (SAR) images, existing deep learning networks face challenges in extracting high-quality vehicle features from SAR images, which impacts vehicle localization accuracy. To address this issue, this paper proposes a vehicle localization method for SAR images based on feature reconstruction and aggregation with rotating boxes. Specifically, our method first employs a backbone network that integrates the space-channel reconfiguration module (SCRM), which contains spatial and channel attention mechanisms specifically designed for SAR images to extract features. The network then connects a progressive cross-fusion mechanism (PCFM) that effectively combines multi-view features from different feature layers, enhancing the information content of feature maps and improving feature representation quality. Finally, these features containing a large receptive field region and enhanced rich contextual information are input into a rotating box vehicle detection head, which effectively reduces false alarms and missed detections. Experiments on a complex scene SAR image vehicle dataset demonstrate that the proposed method significantly improves vehicle localization accuracy. Our method achieves state-of-the-art performance, which demonstrates the superiority and effectiveness of the proposed method. Full article

Low-power wide area network (LPWAN) technologies as part of IoT are gaining a lot of attention as they provide affordable communication over large areas. LoRa and Sigfox as part of LPWAN have emerged as highly effective and promising non-3GPP unlicensed band IoT technologies while challenging the supremacy of cellular technologies for machine-to-machine-(M2M)-based use cases. This paper presents the design goals of LoRa and Sigfox while throwing light on their suitability in congested environments. A practical traffic generator of both LoRa and Sigfox is introduced and further interpolated for understanding simultaneous operation of 100 to 10,000 such nodes in close vicinity while establishing deep understanding on effects of collision, re-transmissions, and link behaviour. Previous work in this field have overlooked simultaneous deployment, collision issues, effects of re-transmission, and propagation profile while arriving at a number of successful receptions. This work uses packet error rate (PER) and delivery ratio, which are correct metrics to calculate successful transmissions. The obtained results show that a maximum of 100 LoRa and 200 Sigfox nodes can be deployed in a fixed transmission use case over an area of up to 1 km. As part of the future scope, solutions have been suggested to increase the effectiveness of LoRa and Sigfox networks. Full article

Cracks pose a critical challenge in the preservation of historical buildings worldwide, particularly in fair-faced walls, where timely and accurate detection is essential to prevent further degradation. Traditional image processing methods have proven inadequate for effectively detecting building cracks. Despite global advancements in deep learning, crack detection under diverse environmental and lighting conditions remains a significant technical hurdle, as highlighted by recent international studies. To address this challenge, we propose an enhanced crack detection algorithm, CL-YOLOv8 (ConvNeXt V2-LSKA-YOLOv8). By integrating the well-established ConvNeXt V2 model as the backbone network into YOLOv8, the algorithm benefits from advanced feature extraction techniques, leading to a superior detection accuracy. This choice leverages ConvNeXt V2’s recognized strengths, providing a robust foundation for improving the overall model performance. Additionally, by introducing the LSKA (Large Separable Kernel Attention) mechanism into the SPPF structure, the feature receptive field is enlarged and feature correlations are strengthened, further enhancing crack detection accuracy in diverse environments. This study also contributes to the field by significantly expanding the dataset for fair-faced wall crack detection, increasing its size sevenfold through data augmentation and the inclusion of additional data. Our experimental results demonstrate that CL-YOLOv8 outperforms mainstream algorithms such as Faster R-CNN, YOLOv5s, YOLOv7-tiny, SSD, and various YOLOv8n/s/m/l/x models. CL-YOLOv8 achieves an accuracy of 85.3%, a recall rate of 83.2%, and a mean average precision (mAP) of 83.7%. Compared to the YOLOv8n base model, CL-YOLOv8 shows improvements of 0.9%, 2.3%, and 3.9% in accuracy, recall rate, and mAP, respectively. These results underscore the effectiveness and superiority of CL-YOLOv8 in crack detection, positioning it as a valuable tool in the global effort to preserve architectural heritage. Full article

In scenarios where global navigation satellite systems (GNSSs) and radio navigation systems are denied, vision-based autonomous landing (VAL) for fixed-wing unmanned aerial vehicles (UAVs) becomes essential. Accurate and real-time runway detection in VAL is vital for providing precise positional and orientational guidance. However, existing research faces significant challenges, including insufficient accuracy, inadequate real-time performance, poor robustness, and high susceptibility to disturbances. To address these challenges, this paper introduces a novel single-stage, anchor-free, and decoupled vision-based runway detection framework, referred to as YOLO-RWY. First, an enhanced data augmentation (EDA) module is incorporated to perform various augmentations, enriching image diversity, and introducing perturbations that improve generalization and safety. Second, a large separable kernel attention (LSKA) module is integrated into the backbone structure to provide a lightweight attention mechanism with a broad receptive field, enhancing feature representation. Third, the neck structure is reorganized as a bidirectional feature pyramid network (BiFPN) module with skip connections and attention allocation, enabling efficient multi-scale and across-stage feature fusion. Finally, the regression loss and task-aligned learning (TAL) assigner are optimized using efficient intersection over union (EIoU) to improve localization evaluation, resulting in faster and more accurate convergence. Comprehensive experiments demonstrate that YOLO-RWY achieves ${\mathrm{AP}}_{50:95}$ scores of 0.760, 0.611, and 0.413 on synthetic, real nominal, and real edge test sets of the landing approach runway detection (LARD) dataset, respectively. Deployment experiments on an edge device show that YOLO-RWY achieves an inference speed of 154.4 FPS under FP32 quantization with an image size of 640. The results indicate that the proposed YOLO-RWY model possesses strong generalization and real-time capabilities, enabling accurate runway detection in complex and challenging visual environments, and providing support for the onboard VAL systems of fixed-wing UAVs. Full article

Object detection technology holds significant promise in unmanned aerial vehicle (UAV) applications. However, traditional methods face challenges in detecting denser, smaller, and more complex targets within UAV aerial images. To address issues such as target occlusion and dense small objects, this paper proposes a multi-scale object detection algorithm based on YOLOv5s. A novel feature extraction module, DCNCSPELAN4, which combines CSPNet and ELAN, is introduced to enhance the receptive field of feature extraction while maintaining network efficiency. Additionally, a lightweight Vision Transformer module, the CloFormer Block, is integrated to provide the network with a global receptive field. Moreover, the algorithm incorporates a three-scale feature fusion (TFE) module and a scale sequence feature fusion (SSFF) module in the neck network to effectively leverage multi-scale spatial information across different feature maps. To address dense small objects, an additional small object detection head was added to the detection layer. The original large object detection head was removed to reduce computational load. The proposed algorithm has been evaluated through ablation experiments and compared with other state-of-the-art methods on the VisDrone2019 and AU-AIR datasets. The results demonstrate that our algorithm outperforms other baseline methods in terms of both accuracy and speed. Compared to the YOLOv5s baseline model, the enhanced algorithm achieves improvements of 12.4% and 8.4% in AP₅₀ and AP metrics, respectively, with only a marginal parameter increase of 0.3 M. These experiments validate the effectiveness of our algorithm for object detection in drone imagery. Full article

In the scenario of power system monitoring, detecting the operating status of circuit breakers is often inaccurate due to variable object scales and background interference. This paper introduces DLCH-YOLO, an object detection algorithm aimed at identifying the operating status of circuit breakers. Firstly, we propose a novel C2f_DLKA module based on Deformable Large Kernel Attention. This module adapts to objects of varying scales within a large receptive field, thereby more effectively extracting multi-scale features. Secondly, we propose a Semantic Screening Feature Pyramid Network designed to fuse multi-scale features. By filtering low-level semantic information, it effectively suppresses background interference to enhance localization accuracy. Finally, the feature extraction network incorporates Generalized-Sparse Convolution, which combines depth-wise separable convolution and channel mixing operations, reducing computational load. The DLCH-YOLO algorithm achieved a 91.8% mAP on our self-built power equipment dataset, representing a 4.7% improvement over the baseline network Yolov8. With its superior detection accuracy and real-time performance, DLCH-YOLO outperforms mainstream detection algorithms. This algorithm provides an efficient and viable solution for circuit breaker status detection. Full article

The advancement of deep learning techniques has significantly propelled the development of the continuous sign language recognition (cSLR) task. However, the spatial feature extraction of sign language videos in the RGB space tends to focus on the overall image information while neglecting the perception of traits at different granularities, such as eye gaze and lip shape, which are more detailed, or posture and gestures, which are more macroscopic. Exploring the efficient fusion of visual information of different granularities is crucial for accurate sign language recognition. In addition, applying a vanilla Transformer to sequence modeling in cSLR exhibits weak performance because specific video frames could interfere with the attention mechanism. These limitations constrain the capability to understand potential semantic characteristics. We introduce a feature fusion method for integrating visual features of disparate granularities and refine the metric of attention to enhance the Transformer’s comprehension of video content. Specifically, we extract CNN feature maps with varying receptive fields and employ a self-attention mechanism to fuse feature maps of different granularities, thereby obtaining multi-scale spatial features of the sign language framework. As for video modeling, we first analyze why the vanilla Transformer failed in cSLR and observe that the magnitude of the feature vectors of video frames could interfere with the distribution of attention weights. Therefore, we utilize the Euclidean distance among vectors to measure the attention weights instead of scaled-dot to enhance dynamic temporal modeling capabilities. Finally, we integrate the two components to construct the model MSF-ET (Multi-Scaled feature Fusion–Euclidean Transformer) for cSLR and train the model end-to-end. We perform experiments on large-scale cSLR benchmarks—PHOENIX-2014 and Chinese Sign Language (CSL)—to validate the effectiveness. Full article