Search Results (31)

Automated livestock monitoring in wide-area grasslands is a critical component of smart agriculture development. Devices such as Unmanned Aerial Vehicles (UAVs), remote sensing, and high-mounted cameras provide unique monitoring perspectives for this purpose. The high-resolution images they capture cover vast grassland backgrounds, where targets often appear as small, distant objects and are extremely unevenly distributed. Applying standard detectors directly to such images yields poor results and extremely high miss rates. To improve the detection accuracy of small targets in high-resolution images, methods represented by Slicing Aided Hyper Inference (SAHI) have been widely adopted. However, in specific scenarios, SAHI’s drawbacks are dramatically amplified. Its strategy of uniform global slicing divides each original image into a fixed number of sub-images, many of which may be pure background (negative samples) containing no targets. This results in a significant waste of computational resources and a precipitous drop in inference speed, falling far short of practical application requirements. To resolve this conflict between accuracy and efficiency, this paper proposes an efficient detection framework named CAMS-AI (Clustering and Adaptive Multi-level Slicing for Aided Inference). CAMS-AI adopts a “coarse-to-fine” intelligent focusing strategy: First, a Region Proposal Network (RPN) is used to rapidly locate all potential target areas. Next, a clustering algorithm is employed to generate precise Regions of Interest (ROIs), effectively focusing computational resources on target-dense areas. Finally, an innovative multi-level slicing strategy and a high-precision model are applied only to these high-quality ROIs for fine-grained detection. Experimental results demonstrate that the CAMS-AI framework achieves a mean Average Precision (mAP) comparable to SAHI while significantly increasing inference speed. Taking the RT-DETR detector as an example, while achieving 96% of the mAP_50–95 accuracy level of the SAHI method, CAMS-AI’s end-to-end frames per second (FPS) is 10.3 times that of SAHI, showcasing its immense application potential in real-world, high-resolution monitoring scenarios. Full article

Accurate vibration measurement is crucial for maintaining the performance, reliability, and safety of automated manufacturing environments. Abnormal vibrations caused by faults in gears or bearings can degrade positional accuracy, reduce productivity, and, over time, significantly impair production efficiency and product quality. Such vibrations may also disrupt supply chains, cause financial losses, and pose safety risks to workers through collisions, falling objects, or other operational hazards. Conventional vibration measurement techniques, such as wired accelerometers and strain gauges, are typically limited to a few discrete measurement points. Achieving multi-point measurements requires numerous sensors, which increases installation complexity, wiring constraints, and setup time, making the process both time-consuming and costly. The integration of high-frame-rate (HFR) cameras with Digital Image Correlation (DIC) enables non-contact, multi-point, full-field vibration measurement of robot manipulators, effectively addressing these limitations. In this study, HFR cameras were employed to perform non-contact, full-field vibration measurements of industrial robots. The HFR camera recorded the robot’s vibrations at 1000 frames per second (fps), and the resulting video was decomposed into individual frames according to the frame rate. Each frame, with a resolution of 1920 × 1080 pixels, was divided into 128 × 128 pixel blocks with a 64-pixel stride, yielding 435 sub-images. This setup effectively simulates the operation of 435 virtual vibration sensors. By applying mask processing to these sub-images, eight key points representing critical robot components were selected for multi-point DIC displacement measurements, enabling effective assessment of vibration distribution and real-time vibration visualization across the entire manipulator. This approach allows simultaneous capture of displacements across all robot components without the need for physical sensors. The transfer function is defined in the frequency domain as the ratio between the output displacement of each robot component and the input excitation applied by the shaker mounted on the end-effector. The frequency–domain transfer functions were computed for multiple robot components, enabling accurate and full-field vibration analysis during operation. Full article

Semantic segmentation of remote sensing imagery is a pivotal task for intelligent interpretation, with critical applications in urban monitoring, resource management, and disaster assessment. Recent advancements in deep learning have significantly improved RS image segmentation, particularly through the use of convolutional neural networks, which demonstrate remarkable proficiency in local feature extraction. However, due to the inherent locality of convolutional operations, prevailing methodologies frequently encounter challenges in capturing long-range dependencies, thereby constraining their comprehensive semantic comprehension. Moreover, the preprocessing of high-resolution remote sensing images by dividing them into sub-images disrupts spatial continuity, further complicating the balance between local feature extraction and global context modeling. To address these limitations, we propose DMA-Net, a Dynamic Morphology-Aware Segmentation Network built on an encoder–decoder architecture. The proposed framework incorporates three primary parts: a Multi-Axis Vision Transformer (MaxViT) encoder achieves a balance between local feature extraction and global context modeling through multi-axis self-attention mechanisms; a Hierarchy Attention Decoder (HA-Decoder) enhanced with Hierarchy Convolutional Groups (HCG) for precise recovery of fine-grained spatial details; and a Channel and Spatial Attention Bridge (CSA-Bridge) to mitigate the encoder–decoder semantic gap while amplifying discriminative feature representations. Extensive experimentation has been conducted to demonstrate the state-of-the-art performance of DMA-Net, which has been shown to achieve 87.31% mIoU on Potsdam, 83.23% on Vaihingen, and 54.23% on LoveDA, thereby surpassing existing methods. Full article

Unmanned Aerial Vehicle (UAV) image semantic segmentation faces challenges in recognizing novel categories due to closed-set training paradigms and the high cost of annotation. While open-vocabulary semantic segmentation (OVSS) leverages vision-language models like CLIP to enable flexible class recognition, existing methods are limited to low-resolution images, hindering their applicability to high-resolution UAV data. Current adaptations—downsampling, cropping, or modifying CLIP—compromise either detail preservation, global context, or computational efficiency. To address these limitations, we propose HR-Seg, the first high-resolution OVSS framework for UAV imagery, which effectively integrates global context from downsampled images with local details from cropped sub-images through a novel cost-volume architecture. We introduce a detail-enhanced encoder with multi-scale embedding and a detail-aware decoder for progressive mask refinement, specifically designed to handle objects of varying sizes in aerial imagery. We evaluated existing OVSS methods alongside HR-Seg, training on the VDD dataset and testing across three benchmarks: VDD, UDD, and UAVid. HR-Seg achieved superior performance with mIoU scores of 89.38, 73.67, and 55.23, respectively, outperforming all compared state-of-the-art OVSS approaches. These results demonstrate HR-Seg’s exceptional capability in processing high-resolution UAV imagery. Full article

To enhance pulsar candidate recognition performance and improve model generalization, this paper proposes the cross-feature hybrid associative prior network (CFHAPNet). CFHAPNet incorporates a novel architecture and strategies to integrate multi-class heterogeneous feature subimages from each candidate into multi-channel data processing. By implementing cross-attention mechanisms and other enhancements for multi-view feature interactions, the model significantly strengthens its ability to capture fine-grained image texture details and weak prior semantic information. Through comparative analysis of feature weight similarity between subimages and average fusion weights, CFHAPNet efficiently identifies and filters genuine pulsar signals from candidate images collected across astronomical observatories. Additionally, refinements to the original loss function enhance convergence, further improving recognition accuracy and stability. To validate CFHAPNet’s efficacy, we compare its performance against several state-of-the-art methods on diverse datasets. The results demonstrate that under similar data scales, our approach achieves superior recognition performance. Notably, on the FAST dataset, the accuracy, recall, and F1-score reach 97.5%, 98.4%, and 98.0%, respectively. Ablation studies further reveal that the proposed enhancements improve overall recognition performance by approximately 5.6% compared to the original architecture, achieving an optimal balance between recognition precision and computational efficiency. These improvements make CFHAPNet a strong candidate for future large-scale pulsar surveys using new sensor systems. Full article

To comprehensively leverage the temporal, static, and dynamic information features of multi-channel surface electromyography (sEMG) signals for gesture recognition, considering the sensitive temporal characteristics of sEMG signals to action amplitude and muscle recruitment patterns, an sEMG-based gesture recognition algorithm is innovatively proposed using Sigimg-GADF-MTF and multi-stream convolutional neural network (MSCNN) by introducing the Sigimg, GADF, and MTF data processing methods and combining them with a multi-stream fusion strategy. Firstly, a sliding window is used to rearrange the multi-channel original sEMG signals through channels to generate a two-dimensional image (named Sigimg method). Meanwhile, each channel signal is respectively transformed into two-dimensional subimages using Gram angular difference field (GADF) and Markov transition field (MTF) methods. Then, the GADF and MTF images are obtained using a horizontal stitching method to splice these subimages, respectively. The Sigimg, GADF, and MTF images are used to construct a training and testing dataset, which is then imported into the constructed MSCNN model for experimental testing. The fully connected layer fusion method is utilized for multi-stream feature fusion, and the gesture recognition results are output. Through comparative experiments, an average accuracy of 88.4% is achieved using the Sigimg-GADF-MTF-MSCNN algorithm on the Ninapro DBl dataset, higher than most mainstream models. At the same time, the effectiveness of the proposed algorithm is fully verified through generalization testing of data obtained from the self-developed sEMG signal acquisition platform with an average accuracy of 82.4%. Full article

Early crop planting area estimation is crucial for achieving effective government resource allocation, optimizing resource distribution planning, and preparation related to food security. Utilizing remote sensing images during the crop growth period for crop planting area estimation has garnered increasing attention. However, area estimation from remote sensing often lags in obtaining image data. Moreover, this method is also influenced by the quality of remote sensing image data and segmentation accuracy. This paper proposes a new method for early area estimation based on multi-year land cover data using a three-dimensional convolutional end-to-end network. This method eliminates the impact of the intermediate process of image segmentation accuracy on area estimation. Additionally, multi-subimage technology is employed to solve the issue of inconsistent input sample size, and label distribution smoothing technology is used to tackle the problem of unbalanced sample distribution. The proposed method was evaluated on U.S. corn and soybean datasets. In comparison to baseline methods, the method achieved relative errors of 0.67% for corn and 3.72% for soybeans at the national level in the United States in 2021. This demonstrates the effectiveness of the proposed method and the potential for early decision-making support. This approach offers a new perspective for area estimation, significantly advancing the timing of planting area prediction and enhancing the accuracy of early area estimation, providing actionable insights for decision-making and resource management. Full article

Given the problem of spatial detail loss and spectral feature degradation in hyperspectral images (HSIs) characterized as blur, often caused by noise during image acquisition, and methods of removing blur noise designed on HSIs being insufficient, we propose an HSI reconstruction network based on a Blur–Kernel–Prior (BKP) method and Spectral–Spatial Attention (SSA) strategy for noise removal and reconstruction of HSIs. Specifically, a grouping strategy is designed to segment the HSIs into spectral dimension sub-images, and the BKP module, based on U-Net, learns the spatially adaptive blur kernel to extract and remove blurred features from each sub-image while preserving spatial features with spatial resolution. Subsequently, the SSA block is employed to extract shallow features, details, and edge information using a hybrid 2D–3D convolution from the sub-images, followed by deep feature extraction using a deep ResNet and multi-head attention (MSA) on the merged image to maximize the preservation of spectral dimension information. The $L_1$ loss function, combined with spectral dimension loss and peak signal-to-noise ratio loss, is utilized to constrain and ensure reconstruction accuracy. Experiments on both synthetic and real datasets demonstrate that our method exhibits excellent performance in reconstructing HSIs affected by blurred noise, outperforming existing methods in terms of quantitative quality and recovery of spectral dimension information. Full article

Medical image registration is essential in clinical practices such as surgical navigation and image-guided diagnosis. The Transformer architecture of TransMorph demonstrates better accuracy in non-rigid registration tasks. However, its weaker spatial locality priors necessitate large-scale training datasets and a heavy number of parameters, which conflict with the limited annotated data and real-time demands of clinical workflows. Moreover, traditional downsampling and upsampling always degrade high-frequency anatomical features such as tissue boundaries or small lesions. We proposed WaveMorph, a wavelet-guided multi-scale ConvNeXt method for unsupervised medical image registration. A novel multi-scale wavelet feature fusion downsampling module is proposed by integrating the ConvNeXt architecture with Haar wavelet lossless decomposition to extract and fuse features from eight frequency sub-images using multi-scale convolution kernels. Additionally, a lightweight dynamic upsampling module is introduced in the decoder to reconstruct fine-grained anatomical structures. WaveMorph integrates the inductive bias of CNNs with the advantages of Transformers, effectively mitigating topological distortions caused by spatial information loss while supporting real-time inference. In both atlas-to-patient (IXI) and inter-patient (OASIS) registration tasks, WaveMorph demonstrates state-of-the-art performance, achieving Dice scores of 0.779 ± 0.015 and 0.824 ± 0.021, respectively, and real-time inference (0.072 s/image), validating the effectiveness of our model in medical image registration. Full article

Azimuth multi-channel techniques show great promise in high-resolution, wide-swath synthetic aperture radar systems. However, in practical engineering applications, errors between channels can significantly affect the reconstruction of multi-channel echo data, leading to a degraded synthetic aperture radar image. To address this issue, this article derives the formula expression in the two-dimensional time domain after single-channel processing under the assumption of an insufficient azimuth sampling rate and proposes a novel algorithm based on the statistical treatment of characteristic clusters. In this algorithm, channel imaging is first performed separately; then, the image is divided into a predefined number of sub-images. The characteristic clusters and points within each sub-image are identified, and their positions, amplitude, and phase information are used to obtain the range synchronization errors, amplitude errors, and phase errors between channels. Compared with traditional methods, the proposed method does not require iteration or the complex eigenvalue decomposition of the covariance matrix. Furthermore, it can utilize existing imaging tools and software in single-channel synthetic aperture radar systems. The effectiveness of the proposed method is validated through simulation experiments and real-world data processing. Full article

Automatically segmenting specific tissues or structures from medical images is a straightforward task for deep learning models. However, identifying a few specific objects from a group of similar targets can be a challenging task. This study focuses on the segmentation of certain specific intervertebral discs from lateral spine images acquired from an MRI scanner. In this research, an approach is proposed that utilizes MultiResUNet models and employs saliency maps for target intervertebral disc segmentation. First, a sub-image cropping method is used to separate the target discs. This method uses MultiResUNet to predict the saliency maps of target discs and crop sub-images for easier segmentation. Then, MultiResUNet is used to segment the target discs in these sub-images. The distance maps of the segmented discs are then calculated and combined with their original image for data augmentation to predict the remaining target discs. The training set and test set use 2674 and 308 MRI images, respectively. Experimental results demonstrate that the proposed method significantly enhances segmentation accuracy to about 98%. The performance of this approach highlights its effectiveness in segmenting specific intervertebral discs from closely similar discs. Full article

Scene-matching navigation is one of the essential technologies for achieving precise navigation in satellite-denied environments. Selecting suitable-matching areas is crucial for planning trajectory and reducing yaw. Most traditional selection methods of suitable-matching areas use hierarchical screening based on multiple feature indicators. However, these methods rarely consider the interrelationship between different feature indicators and use the same set of screening thresholds for different categories of images, which has poor versatility and can easily cause mis-selection and omission. To solve this problem, a suitable-matching areas’ selection method based on multi-level saliency is proposed. The matching performance score is obtained by fusing several segmentation levels’ salient feature extraction results and performing weighted calculations with the sub-image edge density. Compared with the hierarchical screening methods, the matching performance of the candidate areas selected by our algorithm is at least 22.2% higher, and it also has a better matching ability in different scene categories. In addition, the number of missed and wrong selections is significantly reduced. The average matching accuracy of the top three areas selected by our method reached 0.8549, 0.7993, and 0.7803, respectively, under the verification of multiple matching algorithms. Experimental results show this paper’s suitable-matching areas’ selection method is more robust. Full article

In classical radar imaging, such as in Earth remote sensing, electromagnetic waves are usually assumed to propagate in free space. However, in numerous applications, such as ground penetrating radar or non-destructive testing, this assumption no longer holds. When there is a multi-material background, the subsurface image reconstruction becomes considerably more complex. Imaging can be performed in the spatial domain or, equivalently, in the wavenumber domain (k-space). In subsurface imaging, to date, objects with a non-planar surface are commonly reconstructed in the spatial domain, by the Backprojection algorithm combined with ray tracing, which is computationally demanding. On the other hand, objects with a planar surface can be reconstructed more efficiently in k-space. However, many non-planar surfaces are partly planar. Therefore, in this paper, a novel concept is introduced that makes use of the efficient k-space-based reconstruction algorithms for partly planar scenarios, too. The proposed algorithm forms an image from superposing sub-images where as many image parts as possible are reconstructed in the wavenumber domain, and only as many as necessary are reconstructed in the spatial domain. For this, a segmentation scheme is developed to determine which parts of the image volume can be reconstructed in the wavenumber domain. The novel concept is verified by measurements, both from monostatic synthetic aperture radar data and multiple-input–multiple-output radar data. It is shown that the computational efficiency for imaging irregularly shaped geometries can be significantly augmented when applying the proposed concept. Full article

Among recent state-of-the-art realistic image super-resolution (SR) intelligent algorithms, generative adversarial networks (GANs) have achieved impressive visual performance. However, there has been the problem of unsatisfactory perception of super-scored pictures with unpleasant artifacts. To address this issue and further improve visual quality, we proposed a perception-design-oriented PSRGAN with double perception turbos for real-world SR. The first-perception turbo in the generator network has a three-level perception structure with different convolution kernel sizes, which can extract multi-scale features from four $\frac{1}{4}$ size sub-images sliced by original LR image. The slice operation expands adversarial samples to four and could alleviate artifacts during GAN training. The extracted features will be eventually concatenated in later 3 × 2 upsampling processes through pixel shuffle to restore SR image with diversified delicate textures. The second-perception turbo in discriminators has cascaded perception turbo blocks (PTBs), which could further perceive multi-scale features at various spatial relationships and promote the generator to restore subtle textures driven by GAN. Compared with recent SR methods (BSRGAN, real-ESRGAN, PDM_SR, SwinIR, LDL, etc.), we conducted an extensive test with a $\times 4$ upscaling factor on various datasets (OST300, 2020track1, RealSR-Canon, RealSR-Nikon, etc.). We conducted a series of experiments that show that our proposed PSRGAN based on generative adversarial networks outperforms current state-of-the-art intelligent algorithms on several evaluation metrics, including NIQE, NRQM and PI. In terms of visualization, PSRGAN generates finer and more natural textures while suppressing unpleasant artifacts and achieves significant improvements in perceptual quality. Full article

In SAR image registration, most existing methods consider the image registration as a two-classification problem to construct the pair training samples for training the deep model. However, it is difficult to obtain a mass of given matched-points directly from SAR images as the training samples. Based on this, we propose a multi-class double-transformation network for SAR image registration based on Swin-Transformer. Different from existing methods, the proposed method directly considers each key point as an independent category to construct the multi-classification model for SAR image registration. Then, based on the key points from the reference and sensed images, respectively, a double-transformation network with two branches is designed to search for matched-point pairs. In particular, to weaken the inherent diversity between two SAR images, key points from one image are transformed to the other image, and the transformed image is used as the basic image to capture sub-images corresponding to all key points as the training and testing samples. Moreover, a precise-matching module is designed to increase the reliability of the obtained matched-points by eliminating the inconsistent matched-point pairs given by two branches. Finally, a series of experiments illustrate that the proposed method can achieve higher registration performance compared to existing methods. Full article