Search Results (6)

This study introduces Ship-Yolo, a novel algorithm designed to tackle the challenges of detecting small targets against complex backgrounds in remote sensing imagery. Firstly, the proposed method integrates an efficient local attention mechanism into the C3 module of the neck network, forming the EDC module. This enhancement significantly improves the model’s capability to capture critical features, enabling robust performance in scenarios involving intricate backgrounds and multi-scale targets. Secondly, a Lightweight Asymmetric Decoupled Head (LADH-Head) is proposed to separate classification and regression tasks, reducing task conflicts, improving detection performance, and maintaining the model’s lightweight characteristics. Additionally, the LiteConv module is designed to replace the C3 module in the backbone network, leveraging partial convolution to ignore invalid information in occluded regions and avoid misjudgments. Finally, the Content-Aware Reassembly Upsampling Module (CARAFE) is employed to replace the original upsampling module, expanding the receptive field to better capture global information while preserving the lightweight nature of the model. Experiments on the ShipRSImageNet and DOTA datasets demonstrate that Ship-Yolo outperforms other YOLO variants and existing methods in terms of precision, recall, and average precision, exhibiting strong generalization capabilities. Ablation studies further validate the stable performance improvements contributed by the EDC, LADH-Head, LiteConv, and CARAFE modules. Full article

To address the limitations of existing deep learning-based algorithms in detecting surface defects on brake pipe ends, a novel lightweight detection algorithm, FP-YOLOv8, is proposed. This algorithm is developed based on the YOLOv8n framework with the aim of improving accuracy and model lightweight design. First, the C2f_GhostV2 module has been designed to replace the original C2f module. It reduces the model’s parameter count through its unique design. It achieves improved feature representation by adopting specific technique within its structure. Additionally, it incorporates the decoupled fully connected (DFC) attention mechanism, which minimizes information loss during long-range feature transmission by separately capturing pixel information along horizontal and vertical axes via convolution. Second, the Dynamic ATSS label allocation strategy is applied, which dynamically adjusts label assignments by integrating Anchor IoUs and predicted IoUs, effectively reducing the misclassification of high-quality prediction samples as negative samples. Thus, it improves the detection accuracy of the model. Lastly, an asymmetric small-target detection head, FADH, is proposed to utilize depth-separable convolution to accomplish classification and regression tasks, enabling more precise capture of detailed information across scales and improving the detection of small-target defects. The experimental results show that FP-YOLOv8 achieves a mAP50 of 89.5% and an F1-score of 87% on the ends surface defects dataset, representing improvements of 3.3% and 6.0%, respectively, over the YOLOv8n algorithm, Meanwhile, it reduces model parameters and computational costs by 14.3% and 21.0%. Additionally, compared to the baseline model, the AP50 values for cracks, scratches, and flash defects rise by 5.5%, 5.6%, and 2.3%, respectively. These results validate the efficacy of FP-YOLOv8 in enhancing defect detection accuracy, reducing missed detection rates, and decreasing model parameter counts and computational demands, thus meeting the requirements of online defect detection for brake pipe ends surfaces. Full article

Siamese networks have proven to be suitable for many computer vision tasks, including single object tracking. These trackers leverage the siamese structure to benefit from feature cross-correlation, which measures the similarity between a target template and the corresponding search region. However, the linear nature of the correlation operation leads to the loss of important semantic information and may result in suboptimal performance when faced with complex background interference or significant object deformations. In this paper, we introduce the Transformer structure, which has been successful in vision tasks, to enhance the siamese network’s performance in challenging conditions. By incorporating self-attention and cross-attention mechanisms, we modify the original Transformer into an asymmetrical version that can focus on different regions of the feature map. This transformer-like fusion network enables more efficient and effective fusion procedures. Additionally, we introduce a two-layer output structure with decoupling prediction heads, improved loss functions, and window penalty post-processing. This design enhances the performance of both the classification and the regression branches. Extensive experiments conducted on large public datasets such as LaSOT, GOT-10k, and TrackingNet demonstrate that our proposed SiamUT tracker achieves state-of-the-art precision performance on most benchmark datasets. Full article

Object detection in unmanned aerial vehicle (UAV) images is an extremely challenging task and involves problems such as multi-scale objects, a high proportion of small objects, and high overlap between objects. To address these issues, first, we design a Vectorized Intersection Over Union (VIOU) loss based on YOLOv5s. This loss uses the width and height of the bounding box as a vector to construct a cosine function that corresponds to the size of the box and the aspect ratio and directly compares the center point value of the box to improve the accuracy of the bounding box regression. Second, we propose a Progressive Feature Fusion Network (PFFN) that addresses the issue of insufficient semantic extraction of shallow features by Panet. This allows each node of the network to fuse semantic information from deep layers with features from the current layer, thus significantly improving the detection ability of small objects in multi-scale scenes. Finally, we propose an Asymmetric Decoupled (AD) head, which separates the classification network from the regression network and improves the classification and regression capabilities of the network. Our proposed method results in significant improvements on two benchmark datasets compared to YOLOv5s. On the VisDrone 2019 dataset, the performance increased by 9.7% from 34.9% to 44.6%, and on the DOTA dataset, the performance increased by 2.1%. Full article

This paper proposes a high-order MIMO antenna operating at 3.5 GHz for a 5G new radio. Using an eighth-mode substrate integrated waveguide (EMSIW) cavity and considering a typical smartphone scenario, a two-element MIMO antenna is developed and extended to a twelve-element MIMO. These MIMO elements are closely spaced, and by employing multiple diversity techniques, high isolation is achieved without using a decoupling network. The asymmetric EMSIW structures resulted in radiation pattern diversity, and their orthogonal placement provides polarization diversity. The radiation characteristics and diversity performance are parametrically optimized for a two-element MIMO antenna. The experimental results exhibited 6.0 dB and 10.0 dB bandwidths of 250 and 100 MHz, respectively. The measured and simulated radiation patterns are closely matched with a peak gain of 3.4 dBi and isolation ≥36 dB. Encouraged with these results, higher-order MIMO, namely, four- and twelve-element MIMO are investigated, and isolation ≥35 and ≥22 dB are achieved, respectively. The channel capacity is found equal to 56.37 bps/Hz for twelve-element MIMO, which is nearly 6.25 times higher than the two-element counterpart. The hand and head proximity analysis reveal that the proposed antenna performances are within the acceptable limit. A detailed comparison with the previous works demonstrates that the proposed antenna offers a simple, low-cost, and compact MIMO antenna design solution with a high diversity performance. Full article

Capillary gripping is a pick-and-place technique that is particularly well-suited for handling sub-millimetric components. Nevertheless, integrating a fluid supply and release mechanism becomes increasingly difficult to manufacture for these scales. In the present contribution, two hybrid manufacturing procedures are introduced in which the creation of the smallest features is decoupled from the macro-scale components. In the first procedure, small scale features are printed directly (by two-photon polymerisation) on top of a 3D-printed device (through stereolithography). In the second approach, directional ultraviolet (UV)-illumination and an adapted design allowed for successful (polydimethylsiloxane, PDMS) moulding of the microscopic gripper head on top of a metal substrate. Importantly, a fully functional microchannel is present in both cases through which liquid to grip the components can be supplied and retracted. This capability of removing the liquid combined with an asymmetric pillar design allows for a passive release mechanism with a placement precision on the order of 3% of the component size. Full article