Mutual-guided scale-aggregation denoising network for seismic noise attenuation

A multi-scale semantic feature fusion method for remote sensing crop classification

Efficient and accurate identification of highway pavement cracks is crucial for more precise road condition assessment. However, the performance of existing segmentation networks on pavement crack segmentation is often unsatisfactory due to challenges such as interruptions in continuous cracks and misidentifications caused by background noise. To address these issues, this paper proposes a deep learning network model (DCEM) based on multi-scale feature extraction and Dwconv-Edge Encoder feature fusion. Firstly, the Dwconv-Edge Encoder is utilized as the primary branch to extract edge features and contextual information of pavement cracks. Secondly, a dual-channel attention mechanism is integrated with a deep convolutional network, enabling the network to simultaneously focus on different dimensions of crack features. This approach effectively separates target regions, resulting in sharper pavement crack boundaries. Finally, the outputs of the three branches are fused to obtain a prediction map that intuitively determines the recognition results. Experimental results on a dedicated road pavement crack dataset demonstrate that the proposed DCEM model achieves superior performance compared to mainstream models such as HRNet, DeepLabv3+, PSPNet and FCN. Specifically, the DCEM model achieves the highest MIoU score (87.72%) and F1 score (91.82%).

Raman spectroscopy has attracted much attention due to its wide applications in drug detection and many other fields. However, Raman spectra often contain background noise, which poses significant challenges for subsequent analysis and processing. Although various methods for removing background noise have been proposed and have improved analysis accuracy to some extent, these mathematical model-based methods often rely on parameter adjustments based on spectral data to achieve the desired de-noising effect. The introduction of deep learning technology has provided new ideas to solve this problem, breaking through the limitations of traditional methods in parameter dependency. Different deep learning structures exhibit unique advantages when processing different types of data. In this study, we propose a static dropout triangular deep convolutional network (SD-TDCN). This deep learning network can maintain superior performance while significantly reducing the size of model parameters by statically discarding some convolutional blocks in the deep learning network. In addition, this deep learning network also lays an experimental foundation for the subsequent development of deep learning structures with adaptive dropout mechanisms.

In general, most of the existing convolutional neural network (CNN)-based deep-learning models suffer from spatial-information loss and inadequate feature-representation issues. This is due to their inability to capture multiscale-context information and the exclusion of semantic information throughout the pooling operations. In the early layers of a CNN, the network encodes simple semantic representations, such as edges and corners, while, in the latter part of the CNN, the network encodes more complex semantic features, such as complex geometric shapes. Theoretically, it is better for a CNN to extract features from different levels of semantic representation because tasks such as classification and segmentation work better when both simple and complex feature maps are utilized. Hence, it is also crucial to embed multiscale capability throughout the network so that the various scales of the features can be optimally captured to represent the intended task. Multiscale representation enables the network to fuse low-level and high-level features from a restricted receptive field to enhance the deep-model performance. The main novelty of this review is the comprehensive novel taxonomy of multiscale-deep-learning methods, which includes details of several architectures and their strengths that have been implemented in the existing works. Predominantly, multiscale approaches in deep-learning networks can be classed into two categories: multiscale feature learning and multiscale feature fusion. Multiscale feature learning refers to the method of deriving feature maps by examining kernels over several sizes to collect a larger range of relevant features and predict the input images’ spatial mapping. Multiscale feature fusion uses features with different resolutions to find patterns over short and long distances, without a deep network. Additionally, several examples of the techniques are also discussed according to their applications in satellite imagery, medical imaging, agriculture, and industrial and manufacturing systems.

The performance of underwater target detection algorithms is affected by poor imaging quality in underwater environments. Due to the arithmetic power limitation of underwater devices, existing deep learning networks are unable to provide efficient detection processes with high detection accuracy. Lightweight CNN models have been actively applied for underwater environment detection, yet their lite feature fusion networks cannot provide effective fusion effects and reduce the detection accuracy. In this paper, a lightweight algorithm based on multi-scale feature fusion was proposed, with the model parameters greatly reduced, improving the target detection accuracy. The forward propagation memory overhead is reduced by using multi-scale shared convolutional kernels and pooling operations to co-construct the query matrix in the Tansformer encoding stage. Then, the feature fusion path is optimized in order to enhance the connection of multi-scale features. A multiscale feature adaptive fusion strategy is used to enhance the detection performance and reduce the dependence on the complex feature extraction network. The feature extraction network is also reparameterized to simplify the operation. Using the UPRC offshore dataset for validation, the study results have demonstrated that the statistical mAP metrics validate the detection accuracy. Compared with SSD, RetinaNet and YOLOv5-s improved by 13%, 8.6%, and 0.8%, while the number of parameters decreased by 76.09%, 89.74%, and 87.67%. In addition, compared with the YOLOv5-lite model algorithm with the same parameter volume, the mAP is improved by 3.8%, which verifies the accuracy and efficiency of the algorithm in this paper.

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Self-adaptive denoising net: Self-supervised learning for seismic migration artifacts and random noise attenuation

The classification of high-resolution (HR) synthetic aperture radar (SAR) images is of great importance for SAR scene interpretation and application. However, the presence of intricate spatial structural patterns and complex statistical nature makes SAR image classification a challenging task, especially in the case of limited labeled SAR data. This paper proposes a novel HR SAR image classification method, using a multi-scale deep feature fusion network and covariance pooling manifold network (MFFN-CPMN). MFFN-CPMN combines the advantages of local spatial features and global statistical properties and considers the multi-feature information fusion of SAR images in representation learning. First, we propose a Gabor-filtering-based multi-scale feature fusion network (MFFN) to capture the spatial pattern and get the discriminative features of SAR images. The MFFN belongs to a deep convolutional neural network (CNN). To make full use of a large amount of unlabeled data, the weights of each layer of MFFN are optimized by unsupervised denoising dual-sparse encoder. Moreover, the feature fusion strategy in MFFN can effectively exploit the complementary information between different levels and different scales. Second, we utilize a covariance pooling manifold network to extract further the global second-order statistics of SAR images over the fusional feature maps. Finally, the obtained covariance descriptor is more distinct for various land covers. Experimental results on four HR SAR images demonstrate the effectiveness of the proposed method and achieve promising results over other related algorithms.

This paper addresses the problem of rapid, precise, and efficient identification and diagnosis of grape leaf diseases by proposing the Deep-Broad Learning Network Model (ABLSS), which combines a Broad Learning network model with deep learning techniques. The model is optimized using the Adam algorithm based on BLS, and incorporates the LTM mechanism, which significantly enhances learning efficiency, stability, and recognition accuracy. Additionally, by integrating deep learning network optimization techniques, a SENet attention mechanism is added between the mapping and enhancement layers of BLS. Furthermore, based on the U-Net segmentation model, the method integrates dilated spatial pyramid pooling and feature pyramid networks. Dilated convolutions with varying dilation rates are used to capture multi-scale contextual information, which providing rich semantic information and high-resolution details during the decoding process. This improves the ABLSS model’s ability to identify small disease spots. Experimental results show that the ABLSS model achieves the highest recognition accuracy for three types of diseases with similar features on grape leaves, with an average accuracy improvement of 7.69% over BLS and 4.48% over deep learning networks. The MIOU of the segmentation model reaches 86.61%, which is a 6.48% improvement over the original U-Net model, and the MPA is 90.23%, a 8.09% improvement over the original U-Net. These results demonstrate that the proposed method significantly improves the algorithm’s recognition accuracy for small and irregular complex images. The ABLSS model recognizes images 0.375 seconds faster than the deep learning network, achieving a 72.12% speed improvement, thereby significantly enhancing the recognition efficiency of fine features. The ABLSS model combines the high recognition accuracy of deep learning with the fast processing speed of Broad Learning, while overcoming the limitations of BLS in recognizing complex images. This study provides valuable support for the development of smart orchard technologies and the optimization of learning network models.

Object detection (OD) in unmanned aerial vehicle (UAV) images faces many challenges, with diverse-scale objects and small objects being particularly prominent issues. To alleviate these challenges, we propose a novel multiscale feature learning and feature fusion network under the guidance of deformable convolution. First, a deformable convolution-guided feature learning (DCGFL) block is designed in the backbone to extract more effective multiscale features. The DCGFL block leverages the adaptability of deformable convolution to the shapes and scales of objects, akin to spatial attention. Moreover, it also employs channel attention to identify important feature maps. Hence, the proposed backbone possesses the functionality of spatial attention and channel attention. Second, in the neck, we devise a simple generalized feature pyramid network (SimpleGFPN) with several deformable convolution-guided feature fusion (DCGFF) blocks to fuse multiscale features. The proposed neck has cross-layer and cross-scale pathways, facilitating effective information exchange and fusion between shallow spatial and deep semantic features. Third, the SIoU loss is used to better model the bounding box regression loss. Finally, experimental results on the VisDrone2021 and UAVDT datasets show that the proposed method outperforms the compared OD methods. In terms of mean average precision, we obtain 37.8% on VisDrone2021 and 18.5% on UAVDT.

The fully convolutional networks (FCNs) have been widely applied in numerous medical image segmentation tasks. However, tissue regions usually have large variations of shape and scale, so the ability of neural networks to learn multi-scale features is important to the segmentation performance. In this paper, we improve the network for multi-scale feature fusion, in the medical image segmentation by introducing two feature fusion modules: i) global attention multi-scale feature fusion module (GMF); ii) local dense multi-scale feature fusion module (LMF). GMF aims to use global context information to guide the recalibration of low-level features from both spatial and channel aspects, so as to enhance the utilization of effective multi-scale features and suppress the noise of low-level features. LMF adopts bottom-up top-down structure to capture context information, to generate semantic features, and to fuse feature information at different scales. LMF can integrate local dense multi-scale context features layer by layer in the network, thus improving the ability of network to encode interdependent relationships among boundary pixels. Based on the above two modules, we propose a novel medical image segmentation framework (GLF-Net). We evaluated the proposed network and modules on challenging brain tumor segmentation and pancreas segmentation datasets, and very competitive performance has been achieved.

Seismic data recorded in shallow water in the Arctic Ocean contain not only primary reflections but also surface-related multiples with strong amplitudes and short-period characteristics. These multiples generate false stratigraphic boundaries on stacked seismic sections, thereby reducing the accuracy of geological interpretation. Therefore, the attenuation of multiples is an essential step in seismic data processing for accurate geological interpretations. Recently, with the advancement of deep learning technology, research on suppressing surface-related multiples using deep learning networks (such as U-Net and stacked BiLSTM) has been actively proposed.Firstly, surface-related multiple suppression algorithms using U-Net and stacked BiLSTM were applied to Arctic field data respectively. Each algorithm was designed to predict surface-related multiples by using input data that contained both primary reflections and surface-related multiples. Fractional Fourier transform (FrFT) and continuous wavelet transform (CWT), which represent time-series data in the time-frequency domain, were applied to synthetic data and used as input data feature for each network. Finally in order to suppress the surface-related multiples for seismic data in shallow depth Arctic Ocean, the proper methods (network architectures, input data feature) are suggested. AcknowledgmentsThis research was supported by Korea Institute of Marine Science & Technology Promotion (KIMST) funded by the Ministry of Oceans and Fisheries, Korea (RS-2023-00259633). 

Ambient seismic noise beamforming tries to identify the direction (traditional one component beamforming) or the direction and wavetype (three component beamforming) of the incoming ambient noise field. If the signal is weak, either taking longer time intervals or stacking several consecutive time windows is employed to obtain a sharper image of the underlying noise sources. However, this also reduces the temporal resolution of the noise sources and might prevent the identification of distinct sources in the case of a temporally highly variable noise field. In addition, the presence of very local, often station specific, noise sources can compromise the coherence of the seismic noise field, preventing the identification of noise sources. The identification and subsequent removal of either time intervals or single stations with exceptionally low signal correlation could thus also lead to an improvement in the temporal resolution of the seismic noise sources and the classification of the ambient seismic noise field.In this study, we investigate the ambient seismic noise field recorded with different temporary short period seismic networks in the Euregio Meuse-Rhine (EMR). The region is a candidate site for the next generation gravitational wave telescope (Einstein telescope) and characterizing the anthropogenic ambient surface noise field with high spatial and temporal variability containing many different noise sources (e.g. highways, railway lines, industry, wind turbines, urban settlements) is essential. We investigate the spatio-temporal coherence of the seismic wavefield to identify time intervals and regions with high waveform coherence which are then investigated for possible ambient noise sources. The one component and three component (when available) beamforming results are compared with results from matched field processing (MFP) to validate that the sources are outside the recording network and to estimate the possible geographic source area.We observe a clear diurnal character of the coherence of the ambient seismic noise field over a wide frequency range from about 2 to 20 Hz with significantly higher coherence values during night. This indicates the prevalence of very local noise contributions during working hours. In addition, a clear anti-correlation between wavefield coherence and wind speed also indicates the local character of wind generated noise. Limiting beamforming analysis to time windows and stations with high coherence improves the beamforming results and the temporal resolution during time intervals identified as coherent. Beamforming results during time intervals with high waveform coherence often show stable backazimuth directions indicating persistent ambient noise sources. The source location outside the recording network is confirmed by the results of the MFP analysis. This also holds for time intervals during working hours and can be confirmed by MFP processing. Results from such investigations might be used as best practices for the spatio-temporal characterization of ambient noise sources in the case of highly complex noise fields.

Deep learning neural network approach to thermal-wave imaging of damage in solids with application to diffusivity measurements of a green (unsintered) metal powder compact slab

Radio imaging has become instrumental in examining internal anomalies and body organs. The medical expert manually delineates the images in routine practice and reaches the decision. However, manual intervention leads to errors due to human limitations, and the decision becomes operator-dependent. Therefore, automatic liver segmentation from computed tomography (CT) images plays a decisive role in detecting hepatic anomalies, treatment planning, liver transplantation, liver cancer treatment, and post-treatment assessment. Recently deep learning (DL) techniques have proven competence in medical image segmentation. The proposed method is DL-based multiscale feature fusion with channel-wise attention network (MFCA-Net) designed using the computationally efficient Res2Net (R2N) layer, which has the ability to enhance the receptive field of convolutional neural network (CNN) and extract the multiscale information at a more granular level.Further, we reconstructed the multiscale low-level features and fused them with high-level features that enhance the semantic details in the features. In addition, we employed the channel-wise attention mechanism that renovates the features by modelling the interdependencies between the channels and focusing on the prominent features. Also, we altered the low-level features by fusing the renovated features that augment the contextual information, which simplifies the network learning potential. The efficacy of the proposed network was demonstrated on the CHAOS challenge test dataset, where the network attained the DICE of 96.67 ± 0.72%. Thus, the proposed MFCA-Net is computationally efficient, and liver segmentation performance is comparable with state-of-the-art methods.KeywordsMultiscale featuresFeature fusionChannel attentionLiver segmentationCNNCT images