Adjacent Scales Research Articles

Constrained multi-scale dense connections for biomedical image segmentation

Multi-scale dense connection has been widely used in the biomedical image community to enhance the segmentation performance. In this way, features from all or most scales are aggregated or iteratively fused. However, by analyzing the details, we discover that some connections involving distant scales may not contribute to, or even harm, the performance, while they always introduce a noticeable increase in computational cost. In this paper, we propose constrained multi-scale dense connections (CMDC) for biomedical image segmentation. In contrast to current general lightweight approaches, we first introduce two methods, a naive method and a network architecture search (NAS)-based method, to remove redundant connections and verify the optimal connection configuration, thereby improving overall efficiency and accuracy. The results demonstrate that the two approaches obtain a similar optimal configuration in which most features at the adjacent scales are connected. Then, we applied the optimal configuration to various backbone networks to build constrained multi-scale dense networks (CMD-Net). Experimental results evaluated on eight image segmentation datasets covering biomedical images and natural images demonstrate the effectiveness of CMD-Net across a variety of backbone networks (FCN, U-Net, DeepLabV3, SegNet, FCNsa, ConvUNeXt) with a much lower increase in computational cost. Furthermore, CMD-Net achieves state-of-the-art performance on four publicly available datasets. We believe that the CMDC method can offer valuable insight for ways to engage in dense connectivity at multiple scales within communities. The source code has been made available at https://github.com/JerRuy/CMD-Net.

Multimodal registration network with multi-scale feature-crossing.

A critical piece of information for prostate intervention and cancer treatment is provided by the complementary medical imaging modalities of ultrasound (US) and magnetic resonance imaging (MRI). Therefore, MRI-US image fusion is often required during prostate examination to provide contrast-enhanced TRUS, in which image registration is a key step in multimodal image fusion. We propose a novel multi-scale feature-crossing network for the prostate MRI-US image registration task. We designed a feature-crossing module to enhance information flow in the hidden layer by integrating intermediate features between adjacent scales. Additionally, an attention block utilizing three-dimensional convolution interacts information between channels, improving the correlation between different modal features. We used 100 cases randomly selected from The Cancer Imaging Archive (TCIA) for our experiments. A fivefold cross-validation method was applied, dividing the dataset into five subsets. Four subsets were used for training, and one for testing, repeating this process five times to ensure each subset served as the test set once. We test and evaluate our technique using fivefold cross-validation. The cross-validation trials result in a median target registration error of 2.20 mm on landmark centroids and a median Dice of 0.87 on prostate glands, both of which were better than the baseline model. In addition, the standard deviation of the dice similarity coefficient is 0.06, which suggests that the model is stable. We propose a novel multi-scale feature-crossing network for the prostate MRI-US image registration task. A random selection of 100 cases from The Cancer Imaging Archive (TCIA) was used to test and evaluate our approach using fivefold cross-validation. The experimental results showed that our method improves the registration accuracy. After registration, MRI and TURS images were more similar in structure and morphology, and the location and morphology of cancer were more accurately reflected in the images.

Flow field characteristics and drag reduction performance of high–low velocity stripes on the biomimetic imbricated fish scale surfaces

AbstractImproving energy efficiency and cost reduction is a perennial challenge in engineering. Natural biological systems have evolved unique functional surfaces or special physiological functions over centuries to adapt to their complex environments. Among these biological wonders, fish, one of the oldest vertebrate groups, has garnered significant attention due to its exceptional fluid dynamics capabilities. Researchers are actively exploring the potential of fish skin's distinctive structural and material characteristics in reducing resistance. In this study, models of biomimetic imbricated fish scale are established, and the evolution characteristics of the flow field and drag reduction performance on these bionic surfaces are investigated. The results showed a close relationship between the high–low velocity stripes generated and the fluid motion by the imbricated fish scale surface. The stripes' prominence increases with the spacing of the adjacent scales and tilt angle of the fish scale, and the velocity amplitude of the stripes decreases as the exposed length of the imbricated fish scale surface increases. Moreover, the biomimetic imbricated fish scale surface can decrease the velocity gradient and thereby reduce the wall shear stress. The insights gained from the fish skin‐inspired imbricated fish surface provide valuable perspectives for an in‐depth analysis of fish hydrodynamics and offer fresh inspiration for drag reduction and antifouling strategies in engineering applications.

Scale Mutualized Perception for Vessel Border Detection in Intravascular Ultrasound Images.

Vessel border detection in IVUS images is essential for coronary disease diagnosis. It helps to obtain the clinical indices on the inner vessel morphology to indicate the stenosis. However, the existing methods suffer the challenge of scale-dependent interference. Early methods usually rely on the hand-crafted features, thus not robust to this interference. The existing deep learning methods are also ineffective to solve this challenge, because these methods aggregate multi-scale features in the top-down way. This aggregation may bring in interference from the non-adjacent scale. Besides, they only combine the features in all scales, and thus may weaken their complementary information. We propose the scale mutualized perception to solve this challenge by considering the adjacent scales mutually to preserve their complementary information. First, the adjacent small scales contain certain semantics to locate different vessel tissues. Then, they can also perceive the global context to assist the representation of the local context in the adjacent large scale, and vice versa. It helps to distinguish the objects with similar local features. Second, the adjacent large scales provide detailed information to refine the vessel boundaries. The experiments show the effectiveness of our method in 153 IVUS sequences, and its superiority to ten state-of-the-art methods.

A multi-scale information integration framework for infrared and visible image fusion

Infrared and visible image fusion aims at generating a fused image containing the intensity and detail information of source images, and the key issue is effectively measuring and integrating the complementary information of multi-modality images from the same scene. Existing methods mostly adopt a simple weight in the loss function to decide the information retention of each modality rather than adaptively measuring complementary information for different image pairs. In this study, we propose a multi-scale dual attention (MDA) framework for infrared and visible image fusion, which is designed to measure and integrate multi-scale complementary information in both structure and loss function at the image and patch level. In our method, the residual downsample block decomposes source images into three scales first. Then, dual attention fusion block integrates complementary information and generates a spatial and channel attention map at the same and adjacent scale for feature fusion. Finally, the output image is reconstructed by the residual reconstruction block. Loss function consists of image-level, feature-level and patch-level three parts, of which the calculation of the image-level and patch-level two parts are based on the weights generated by the complementary information measurement. Indeed, to constrain the pixel intensity distribution between the output and infrared image, a style loss is added. Our fusion results perform robust and informative across different scenarios. Qualitative and quantitative results on three datasets illustrate that our method is able to preserve both thermal radiation and detailed information from two modalities and achieve comparable results compared with the other state-of-the-art methods. Ablation experiments show the effectiveness of our information integration architecture and adaptively measure complementary information retention in the loss function. Our code is available at https://github.com/SSyangguang/MDA.

The health implications of neighborhood networks based on daily mobility in US cities

A large body of research has been dedicated to understanding the neighborhood conditions that impact health, which outcomes are affected, and how these associations vary by demographic and socioeconomic neighborhood and individual characteristics. This literature has focused mostly on the neighborhoods in which individuals reside, thus failing to recognize that residents across race/ethnicity and class spend a non-trivial amount of their time in neighborhoods far from their residential settings. To address this gap, we use mobile phone data from the company SafeGraph to compare racial inequality in neighborhood socioeconomic advantage exposure across three scales: the neighborhoods that residents live in, their adjacent neighborhoods, and the neighborhoods that they regularly visit. We found that the socioeconomic advantage levels in neighborhood networks differ from the levels at the residential and adjacent scales across all ethnoracial neighborhoods. Furthermore, socioeconomic advantage at the network level is associated with diabetes and hypertension prevalence above and beyond its impact at the residential and adjacent levels. We also find ethnoracial differences in these associations, with greater beneficial consequences of network socioeconomic advantage exposure on hypertension and diabetes for white neighborhoods. Future social determinants of health research needs to reconceptualize exposure to include the larger neighborhood network that a community is embedded in based on where their residents travel to and from.

FFEDet: Fine-Grained Feature Enhancement for Small Object Detection

Small object detection poses significant challenges in the realm of general object detection, primarily due to complex backgrounds and other instances interfering with the expression of features. This research introduces an uncomplicated and efficient algorithm that addresses the limitations of small object detection. Firstly, we propose an efficient cross-scale feature fusion attention module called ECFA, which effectively utilizes attention mechanisms to emphasize relevant features across adjacent scales and suppress irrelevant noise, tackling issues of feature redundancy and insufficient representation of small objects. Secondly, we design a highly efficient convolutional module named SEConv, which reduces computational redundancy while providing a multi-scale receptive field to improve feature learning. Additionally, we develop a novel dynamic focus sample weighting function called DFSLoss, which allows the model to focus on learning from both normal and challenging samples, effectively addressing the problem of imbalanced difficulty levels among samples. Moreover, we introduce Wise-IoU to address the impact of poor-quality examples on model convergence. We extensively conduct experiments on four publicly available datasets to showcase the exceptional performance of our method in comparison to state-of-the-art object detectors.

VCAFusion: An infrared and visible image fusion network with visual perception and cross-scale attention

Infrared and visible image fusion methods aim to combine salient target instances and abundant texture details into fused images. However, due to the interference of harsh conditions, such as dense smoke, fog, and intense light, it is feasible for external interference information to be integrated into the fused image, which seriously affects the image quality. To this end, we propose an infrared and visible image fusion network with visual perception and cross-scale attention modules, termed VCAFusion, which integrates critical information from source images in harsh conditions more efficiently. Specifically, considering that the human eye can identify key information under adverse conditions, we design a visual perception module (VPM), guiding information integration from the perspective of human visual perception. In addition, we propose a cross-scale attention module (CSAM) based on shifted window cross-attention, which aims to capture the long-distance correlation between adjacent scale features, providing more accurate image information for image restoration. Experiments with a variety of datasets reveal that the VCAFusion can adaptively retain image information and further improve image generation ability in harsh conditions.

SingleS2R: Single sample driven Sim-to-Real transfer for Multi-Source Visual-Tactile Information Understanding using multi-scale vision transformers

Due to variations in light transmission and wear on the contact head, existing visual-tactile dataset building methods typically require a large amount of real-world data, making the dataset building process time-consuming and labor-intensive. Sim-to-Real learning has been proposed to realize Multi-Source Visual-Tactile Information Understanding (MSVTIU) in simulate and real environment, which can efficiently promote visual-tactile dataset building using simulation method for emerged robotic applications. However, the existing Sim-to-Real learning also requires more than 10,000 real data, while the corresponding data need to be re-collected when the sensor version changes. To address this challenge, we propose a powerful Sim-to-Real transfer for MSVTIU which requires only one single real-world tactile sample. To effectively extract features from the single real tactile sample, a multi-scale vision transformers-based Generative Adversarial Network (GAN) is proposed to address MSVTIU task under extremely limited data. We introduce a novel scale-dependent self-attention mechanism that allows attention layers to adapt their behavior at different stages of the generating process. In addition, we introduced a residual block for capturing contextual information between adjacent scales, which utilizes shortcut connections to fully preserve texture and structure information. We subsequently enhanced the model understanding of visual-tactile information using elastic transform and adaptive adversarial training strategy, both of which are designed specifically for MSVTIU. Experiments on two public datasets with diverse objects indicate that our Sim-to-Real transfer approach utilizing only one single real-world visual-tactile sample outperforms the state-of-the-art methods that requires tens of thousands of samples.

Improving the Application of Yolov7 Algorithm in Pin-Losing-Bolts Detection on Power Transmission Lines

A method for bolt deficiency detection on power transmission lines based on YOLOv7 is proposed to address the issues of low detection accuracy and high false negatives in current unmanned aerial vehicle (UAV) inspections. In the Neck module, the existing feature fusion structure is modified by directly combining deep and shallow feature information across adjacent scale feature maps. The prior box sizes in the original YOLOv7 are adjusted to better fit the dimensions and aspect ratios of bolt targets. The improved YOLOv7 algorithm enhances the learning capability of bolt feature information. Experimental results on the bolt deficiency dataset using this method show a 6% increase in precision and a 0.6% increase in mAP_0.5. The experiments demonstrate that the improved method enhances the detection ability of bolt deficiencies on power transmission lines and has practical value in intelligent inspections.

Distinctive Phase Interdependency Model for Retinal Vasculature Delineation in OCT-Angiography Images.

Automatic detection of retinal vasculature in optical coherence tomography angiography (OCTA) images faces several challenges such as the closely located capillaries, vessel discontinuity and high noise level. This paper introduces a new distinctive phase interdependency model to address these problems for delineating centerline patterns of the vascular network. We capture the inherent property of vascular centerlines by obtaining the inter-scale dependency information that exists between neighboring symmetrical wavelets in complex Poisson domain. In particular, the proposed phase interdependency model identifies vascular centerlines as the distinctive features that have high magnitudes over adjacent symmetrical coefficients whereas the coefficients caused by background noises are decayed rapidly along adjacent wavelet scales. The potential relationships between the neighboring Poisson coefficients are established based on the coherency of distinctive symmetrical wavelets. The proposed phase model is assessed on the OCTA-500 database (300 OCTA images + 200 OCT images), ROSE-1-SVC dataset (9 OCTA images), ROSE-1 (SVC+ DVC) dataset (9 OCTA images), and ROSE-2 dataset (22 OCTA images). The experiments on the clinically relevant OCTA images validate the effectiveness of the proposed method in achieving high-quality results. Our method produces average FScore of 0.822, 0.782, and 0.779 on ROSE-1-SVC, ROSE-1 (SVC+ DVC), and ROSE-2 datasets, respectively, and the FScore of 0.910 and 0.862 on OCTA_6mm and OCT_3mm datasets (OCTA-500 database), respectively, demonstrating its superior performance over the state-of-the-art benchmark methods.

Plantness, Animalness, and Humanness: plant placement within animacy and adjacent scales

AbstractAnimacy is an important framework through which humans view and categorize the world, but many objects do not easily fit within this scale. Plants are unique because they are very familiar to humans, yet the features and traits relevant for placement within the animacy scale are generally poorly understood by the public. Animacy occurs at three levels, with the inherent attributes of the object (biology), how they are perceived (cognition), and how they are expressed in languages (linguistics). Animacy is dependent on qualification and perception as alive, mobile, and intentional. In the absence of visible movement, classification is dependent on featural attributes indicating mobility or placement in a group recognized as animate (animalness). Plants have complicated bodies whose forms and structures are frequently clear representations of their life history and function (plantness), more than many animals, yet these signs of movement and activity are rarely recognized. The animacy scale may be more closely based on human similarity (humanness) with humans as the peak of life, mobility, and intentionality. As humans, we can have an anthropocentric viewpoint, rendering plants as scenery or utility, or use anthropomorphic interaction to better understand and recognize the dynamic lives of plants. The goal of this review is to compare the current evidence on the placement of plants within animacy and adjacent scales with the biology and habit of land plants, to better understand human perception and behaviour, and work with this process to educate and inform people about the complex lives of plants.

Iterative Edge Enhancing Framework for Building Change Detection

The <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Building Change Detection</i> (BCD) task serves urban planning through monitoring the landuse. However, due to the complexity of remote sensing images and high foreground-background similarity, it leads to inaccurate detection of building edge regions. Existing methods deal with this problem by fusing features of different layers. But the fusing operation cannot separate details information from overall information of buildings, resulting in inaccurate detection of building edge area. To address the above challenges, we propose an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Iterative Edge Enhancing Framework</i> (IEEF). The IEEF alleviates the building edge detection difficulty by densely implementing Detail Semantic Enhancement Module in decoding part. This module takes differential features between adjacent scales to explicitly represent the building edge information. Simultaneously, to deal with the classes imbalance problem, a Density-Guided Sampling method dedicated for change detection is proposed to increase the proportion of positive samples during training. Our proposed method achieves state-of-the-art performance on the LEVIR-CD dataset and the WHU dataset, and obtains accurate changed building edges.

PSRR-MaxpoolNMS++: Fast Non-Maximum Suppression with Discretization and Pooling.

Non-maximum suppression (NMS) is an essential post-processing step for object detection. The de-facto standard for NMS, namely GreedyNMS, is not parallelizable and could thus be the performance bottleneck in object detection pipelines. MaxpoolNMS is introduced as a fast and parallelizable alternative to GreedyNMS. However, MaxpoolNMS is only capable of replacing the GreedyNMS at the first stage of two-stage detectors like Faster R-CNN. To address this issue, we observe that MaxpoolNMS employs the process of box coordinate discretization followed by local score argmax calculation, to discard the nested-loop pipeline in GreedyNMS to enable parallelizable implementations. In this paper, we introduce a simple Relationship Recovery module and a Pyramid Shifted MaxpoolNMS module to improve the above two stages, respectively. With these two modules, our PSRR-MaxpoolNMS is a generic and parallelizable approach, which can completely replace GreedyNMS at all stages in all detectors. Furthermore, we extend PSRR-MaxpoolNMS to the more powerful PSRR-MaxpoolNMS++. As for box coordinate discretization, we propose Density-based Discretization for better adherence to the target density of the suppression. As for local score argmax calculation, we propose an Adjacent Scale Pooling scheme for mining out the duplicated box pairs more accurately and efficiently. Extensive experiments demonstrate that both our PSRR-MaxpoolNMS and PSRR-MaxpoolNMS++ outperform MaxpoolNMS by a large margin. Additionally, PSRR-MaxpoolNMS++ not only surpasses PSRR-MaxpoolNMS but also attains competitive accuracy and much better efficiency when compared with GreedyNMS. Therefore, PSRR-MaxpoolNMS++ is a parallelizable NMS solution that can effectively replace GreedyNMS at all stages in all detectors.

On the Occurrence of the Gar Obaichthys africanus Grande in the Cretaceous of Portugal: Palaeoecological and Palaeobiogeographical Implications

Several disarticulated fish scales and a vertebral centrum were collected from the uppermost middle to lowermost upper Cenomanian beds of the vertebrate fossil site of Casais dos Carecos (Baixo Mondego region, Coimbra, West Portugal), corresponding to shallow carbonate and mixed facies (“Unit B”) of the Tentúgal Formation. The taphonomic preservation of these remains is adequate for their detailed taxonomical study. The scales are diagnosable for the species Obaichthys africanus Grande, as each one has a strong spine protruding from the middle of the posterior border in a rostrocaudal direction, a dorsoventral peg and socket, and a small anterodorsal process for articulation of adjacent scales. The sculpture with ganoid ridges and grooves distinguishes the studied remains from those of O. decoratus Wenz and Brito, which display rounded tubercles. The isolated Lepisosteoidea centrum is tentatively attributed to O. africanus as well, as it was found together with the scales, and no other compatible remains were found in the site. The fish material reported here constitutes the first record of O. africanus in the Baixo Mondego region and northern ranges of the Albian–Turonian West Portuguese Carbonate Platform, as well as in the uppermost middle to basal upper Cenomanian of Portugal.

Wetland water quality patterns and anthropogenic pressure associations across the continental USA.

Anthropogenic impacts on lake and stream water quality are well established but have been much less studied in wetlands. Here we use data from the 2016 National Wetland Condition Assessment to characterize water quality and its relationship to anthropogenic pressure for inland wetlands across the conterminous USA. Water samples obtained from 525 inland wetlands spanned pH from <4 to >9 and 3 to 5 orders of magnitude in ionic strength (chloride, sulfate, conductivity), nutrients (total N and P), turbidity, planktonic chlorophyll, and dissolved organic carbon (DOC). Anthropogenic pressure levels were evaluated at two spatial scales - an adjacent scale scored from field checklists, and a catchment scale indicated by percent agricultural plus urban landcover. Pressure at the two spatial scales were uncorrelated and varied considerably across regions and wetland hydrogeomorphic types. Both adjacent- and catchment-scale pressure were associated with elevated ionic-strength metrics; chloride elevation was most evident in road-salt using states, and sulfate was strongly elevated in a few sites with coal mining nearby. Nutrients were elevated in association with catchment-scale pressure but concomitant changes were not seen in planktonic chlorophyll. Acidic pH and high DOC occurred primarily in upper Great Lakes and eastern seaboard sites having low anthropogenic pressure, suggesting natural organic acid sources. Ionic strength and nutrients increased with increasing catchment-scale pressure even in Flats and closed Depression and Lacustrine sites, which indicates connectivity to rather than isolation from upland anthropogenic landuse even for wetlands lacking inflowing streams.

High-precision target ranging in complex orchard scenes by utilizing semantic segmentation results and binocular vision

The automation of orchard production is increasingly relying on robotics, driven by the advancements in artificial intelligence technology. However, accurately comprehending semantic information and precisely locating various targets within orchard environments remain challenges. Current research often relies on expensive multi-sensor fusion techniques or vision-only approaches that yield inadequate segmentation outcomes for perceiving orchard surroundings. To address these issues, this article proposes a novel approach for target ranging in complex orchard scenes, leveraging semantic segmentation results. The article introduces the MsFF-Segformer model, which employs multi-scale feature fusion to generate high-precision semantic segmentation images. The model incorporates the MiT-B0 encoder, which utilizes a pure attention mechanism, and the MsFF decoder, specifically designed for multi-scale feature fusion. The MsFF decoder includes the AFAM module to effectively align features of adjacent scales. Additionally, the channel attention module and depth separable convolution module are introduced to reduce model parameter size and obtain feature vectors with rich semantic levels, enhancing the segmentation performance of multi-scale targets in orchards. Based on the accurate semantic segmentation outcomes in orchard environments, this study introduces a novel approach named TPDMR that integrates binocular vision to estimate the distances of various objects within orchards. Firstly, the process involves matching the semantic category matrix with the depth information matrix. Subsequently, the depth information array that represents the target category is obtained, and any invalid depth information is filtered out. Finally, the average depth of the target is calculated. Evaluation of the MsFF-Segformer model on a self-made orchard dataset demonstrates superior performance compared to U-net and other models, achieving a Mean Intersection over Union (MIoU) of 86.52 % and a Mean Pixel Accuracy (MPA) of 94.05 %. The parameters and prediction time for a single frame are 15.1 M and 0.019 s, respectively. These values are significantly lower than those of U-net, Deeplabv3+, and Hrnet models, with reductions of 84.1 %, 32.5 %, 5.9 % and 69.4 %, 59.7 %, 64.2 % respectively. The TPDMR method demonstrates a high level of accuracy and stability in target ranging, with a ranging error of less than 6 % across all targets. Furthermore, the overall algorithm runtime is estimated to be approximately 0.8 s, indicating efficient performance.

Application of Swin-Unet for pointer detection and automatic calculation of readings in pointer-type meters

Pointer-type meters are widely used in military, industrial, and aerospace applications. In this paper, we propose a method to automatically calculate the readings of pointer-type meters that exhibits strong robustness to various situations, such as complex backgrounds, tilted meters, blurred images, and meter images with uneven illumination. First, the mask maps of scale and pointers are obtained using the Swin-Unet semantic segmentation network. For the mask map of scale, the Swin Transformer image classification network is used to identify the values of the scale and the coordinates of the centroids of the scale, and for the mask map of the pointer, the least skeleton circle method is proposed to fit the linear equation of the pointer. Second, the influence of the pointer and several adjacent scale on the meter reading is considered, and the weighted angle method (WAM) is proposed to calculate the meter reading. In order to verify the robustness of the algorithm in this paper, the pointer detection method is compared with the traditional pointer detection method, and it is found that the pointer detection method in this paper works better, and the pointer detection algorithm in this paper is applied to different semantic segmentation results, and it is verified that the pointer detection algorithm in this paper can be well adapted to different semantic segmentation results. This paper also compares the proposed algorithm with the existing meter reading calculation methods. The experiments show that using WAM on uncorrected meter images reduces the error by 30% compared with the traditional angle method, and using WAM on corrected meter images reduces the error by about 50%, which finally verifies the effectiveness of the algorithm in this paper.

DMNet: Dynamic Memory Network for RGB-D Salient Object Detection

RGB-D salient object detection aims to identify the most salient object using the color and depth information of images. Currently, most of the existing salient object detection models use the classical U-Net architecture, which uses up-sampling and short link decoding to exploit saliency cues after generating multi-level features by successive convolution and pooling operations. However, the multi-level encoding and progressive up-sampling decoding used by these models may lose some of the high-level semantic information during feature extraction and information fusion and some of the detailed information during image recovery, which in turn affects the quality of generated saliency maps. To solve these problems, we propose a dynamic memory network (DMNet) consisting of an interactive enhancement encoder and a dynamic memory decoder, which achieves high-precision detection of salient objects with a more complete and superior encoding and decoding strategy. Specifically, in the interactive enhancement encoder, we propose a feature interactive fusion module (FIFM), which can enhance intermediate-scale RGB features by fusing RGB features of three adjacent scales. Moreover, we design a depth-guided dense fusion module (DDFM) to fuse the features from RGB and depth modalities. In the dynamic memory decoder, we design a full-dimensional dynamic convolutional expansion module (FDCEM) to enhance the information representation capability of features at different scales. Furthermore, we also design a gated decoding module (GDM) to decode features of different scales and eliminate non-salient information. Extensive experimental results on STERE, SIP, NLPR, NJU2K, SSD, and DES datasets demonstrate that our model outperforms most of the state-of-the-art RGB-D SOD methods. In addition, the experimental results on three RGB-T datasets, VT821, VT1000, and VT5000 also show that our model can be effectively used for RGB-T SOD.

A novel seismic random noise suppression method based on wavelet threshold and Lipschitz

The seismic random noise suppression is very important in the processing and interpretation of seismic data. Wavelet transform is an effective tool to remove random noise. Aiming at the problems of signal propagation point omission and misselection, insignificant denoising effect and poor stability of the traditional wavelet maximum mode (WMM) method, this paper proposes an improved wavelet mode maximum value (IMWMM) denoising method. The Lipschitz of wavelet transform with signal and noise has different features used to distinguish signal and noise. Comparing the propagation points of adjacent scales and removing the points with reduced mode values achieve the separation of seismic signal and noise. The synthetic data, Stanford Earthquake Dataset (STEAD) data and real-field seismic signal experimental results prove the validity of the IMWMM method for both suppressing random noise and preserving seismic signal. The real-field seismic data came from Wenchuan experimental results present that the proposed IMWMM method has effectiveness of random noise suppression with SNR above 28.4527 dB, that has improvement for quality of seismic data.