Mapping Module Research Articles

Collaborative Consistent Knowledge Distillation Framework for Remote Sensing Image Scene Classification Network

For remote sensing image scene classification tasks, the classification accuracy of the small-scale deep neural network tends to be low and fails to achieve accuracy in real-world application scenarios. However, although large deep neural networks can improve the classification accuracy of remote sensing image scenes to some extent, the corresponding deep neural networks also have more parameters and cannot be used on existing embedded devices. The main reason for this is that there are a large number of redundant parameters in large deep networks, which directly leads to the difficulty of application on embedded devices and also reduces the classification speed. Considering the contradiction between hardware equipment and classification accuracy requirements, we propose a collaborative consistent knowledge distillation method for improving the classification accuracy of remote sensing image scenes on embedded devices, called CKD. In essence, our method addresses two aspects: (1) We design a multi-branch fused redundant feature mapping module, which significantly improves the parameter redundancy problem. (2) To improve the classification accuracy of the deep model on embedded devices, we propose a knowledge distillation method based on mutually supervised learning. Experiments were conducted on two remote sensing image classification datasets, SIRI-WHU and NWPU-RESISC45, and the experimental results showed that our approach significantly reduced the number of redundant parameters in the deep network; the number of parameters decreased from 1.73 M to 0.90 M. In addition, compared to a series of student sub-networks obtained based on the existing different knowledge distillation methods, the performance of the student sub-networks obtained by CKD for remote sensing scene classification was significantly improved on two different datasets, with an average accuracy of 0.943 and 0.916, respectively.

Battery storage system plug-and-play information flow implementation technology

In order to solve the problems that may exist in the large-scale application of energy storage, the “plug-and-play” technology is realized through battery storage power plants. The concept of plug-and-play originates from the network, which refers to the ability of the computer system to configure expansion boards and other devices automatically. This paper researches plug-and-play key technologies for battery storage power stations, aiming to overcome the grid-connected bottlenecks after large-scale application of energy storage systems, improve the effectiveness and convenience of the grid-connected operation of energy storage systems, and effectively improve the practicality of energy storage systems level, supporting the company’s energy Internet development strategy. Based on the technical framework of plug-and-play realization of battery storage power stations, this paper will conduct technical research on the realization of information flow. First, based on the IED modeling method and the actual functional requirements of BESS, we select logical nodes with corresponding functions to form logical devices and establish the BESS information model. Then, we express the self-describing characteristics through the SCL configuration file and analyze the configuration process of the configuration description file CID. Finally, the plug-and-play information flow implementation architecture is constructed with the heterogeneous information model mapping and data conversion module as the core part. Our design can realize the real plug-and-play operation of the battery storage power station connected to the regional power grid, thereby promoting the friendly interaction between the regional power grid and the battery storage power station and improving the adaptability of the battery storage power station in different application scenarios.

Regulating Surface Reaction Kinetics through Ligand Field Effects for Fast and Reversible Aqueous Zinc Batteries

AbstractDesigning water‐deficient solvation sheath of Zn2+ by ligand substitution is a widely used strategy to protect Zn metal anode, yet the intrinsic tradeoff between Zn nucleation/dissolution kinetics and the side hydrogen evolution reaction (HER) remains a huge challenge. Herein, we find boric acid (BA) with moderate ligand field interaction can partially replace H2O molecules in the solvation sheath of Zn2+, forming a stable water‐deficient solvation sheath. It enables fast Zn nucleation/dissolution kinetics and substantially suppressed HER. Crucially, by systematically comparing the ligand field strength and solvation energies between BA and the ever‐reported electrolyte additives, we also find that the solvation energy has a strong correlation with Zn nucleation/dissolution kinetics and HER inhibition ability, displaying a classic volcano behavior. The modulation map could provide valuable insights for solvation sheath design of zinc batteries and beyond.

Regulating Surface Reaction Kinetics through Ligand Field Effects for Fast and Reversible Aqueous Zinc Batteries.

Designing water-deficient solvation sheath of Zn2+ by ligand substitution is a widely used strategy to protect Zn metal anode, yet the intrinsic tradeoff between Zn nucleation/dissolution kinetics and the side hydrogen evolution reaction (HER) remains a huge challenge. Herein, we find boric acid (BA) with moderate ligand field interaction can partially replace H2 O molecules in the solvation sheath of Zn2+ , forming a stable water-deficient solvation sheath. It enables fast Zn nucleation/dissolution kinetics and substantially suppressed HER. Crucially, by systematically comparing the ligand field strength and solvation energies between BA and the ever-reported electrolyte additives, we also find that the solvation energy has a strong correlation with Zn nucleation/dissolution kinetics and HER inhibition ability, displaying a classic volcano behavior. The modulation map could provide valuable insights for solvation sheath design of zinc batteries and beyond.

Salient object detection in low-light images via functional optimization-inspired feature polishing

Salient object detection under low-light conditions remains a challenge in many practical applications. Most recent works focus on feature integration without considering filtering out clutter from the darkness, thus limiting the detection performance. To tackle this issue, we propose a low-light image salient object detection network (LLISOD), which generates highly accurate saliency maps by functional optimization-inspired feature polishing strategy. The LLISOD includes: (1) An unfolded implicit nonlinear mapping (UINM) module uniquely designed for polishing feature maps; and (2) the hierarchical feature polishing (HFP) streams proposed for fusing the outputs of the UINM module on the top-down pathway to refine the saliency predictions. Furthermore, we provide a new dataset for benchmarking the investigation of salient object detection in low-light images. Extensive experiments demonstrate that our method outperforms existing state-of-the-art approaches. Code will be available at https://github.com/yuehuihui000/LLISOD.

A self-attention based global feature enhancing network for semantic segmentation of large-scale urban street-level point clouds

• A novel network for semantic segmentation of large-scale urban point clouds. • A self-attention-based channel-wisely enhanced global feature is constructed. • A weighted semantic mapping module for highly accurate semantic segmentation. Point clouds of large-scale urban street scenes contain large quantities of object categories and rich semantic information. The semantic segmentation is the basis and key to subsequent essential applications, such as digital twin engineering and city information model. The global feature of point clouds in large-scale scenes can provide long-range context information, which is critical to high-quality semantic segmentation. However, the learning of global spatial saliency considering class label constraints is often ignored in the feature representation of some deep learning models. With regard to this, we propose a Global Feature Self-Attention Encoding (GFSAE) module and a Weighted Semantic Mapping (WSM) module to make the semantic segmentation model of point clouds in large-scale urban street scene focus more on the global salient feature expression by self-attention enhancement channel by channel and take into account the constraints of semantic categories to learn a better semantic segmentation model for urban street scenes. The experiments are performed on the Semantic3D dataset and our own collected vehicle Mobile Laser Scanning (MLS) point cloud dataset. The segmentation results show that the GFSAE and the WSM proposed by us can improve the semantic segmentation of point clouds in large-scale urban street scenes and prove the effectiveness of our model compared with other state-of-the-art methods.

Self-adjusting multilayer nonlinear coupled mapping for low-resolution face recognition

In practical surveillance scenes, effective recognition of low-resolution (LR) images is an urgent issue. At present, the improvement of methods for LR image recognition tasks mainly focuses on how to effectively extract information from LR images. This paper explores a novel self-adjusting multilayer nonlinear coupled mapping (SMNCM) network. The proposed SMNCM includes two main components, the multilayer nonlinear coupled mapping (MNCM) module, which is the feature extractor, and the self-adjusting feature fusion (SaFF) module. In the MNCM module, the LR template image set and multiple different high-resolution template image sets are used to construct a pyramid-like multicoupled mapping feature extraction network. In the SaFF module, the fusion weights of multiple features and the other parameters are collaboratively learned for the purpose of correct classification by the gradient learning network. To achieve this goal, a new gradient optimization model for fusion weights and other parameters is constructed. The features fused by the learned weights and the multiple features of the MNCM module are more suitable for classification tasks. Experimental results indicate that on the five databases, our proposed method outperforms the state-of-the-art approaches for LR face recognition. The ablation experiment suggests that each module in the proposed method can contribute to improving the LR image recognition performance.

Automatic Defect Description of Railway Track Line Image Based on Dense Captioning.

The state monitoring of the railway track line is one of the important tasks to ensure the safety of the railway transportation system. While the defect recognition result, that is, the inspection report, is the main basis for the maintenance decision. Most previous attempts have proposed intelligent detection methods to achieve rapid and accurate inspection of the safety state of the railway track line. However, there are few investigations on the automatic generation of inspection reports. Fortunately, inspired by the recent advances and successes in dense captioning, such technologies can be investigated and used to generate textual information on the type, position, status, and interrelationship of the key components from the field images. To this end, based on the work of DenseCap, a railway track line image captioning model (RTLCap for short) is proposed, which replaces VGG16 with ResNet-50-FPN as the backbone of the model to extract more powerful image features. In addition, towards the problems of object occlusion and category imbalance in the field images, Soft-NMS and Focal Loss are applied in RTLCap to promote defect description performance. After that, to improve the image processing speed of RTLCap and reduce the complexity of the model, a reconstructed RTLCap model named Faster RTLCap is presented with the help of YOLOv3. In the encoder part, a multi-level regional feature localization, mapping, and fusion module (MFLMF) are proposed to extract regional features, and an SPP (Spatial Pyramid Pooling) layer is employed after MFLMF to reduce model parameters. As for the decoder part, a stacked LSTM is adopted as the language model for better language representation learning. Both quantitative and qualitative experimental results demonstrate the effectiveness of the proposed methods.

Challenging Environments for Precise Mapping Using GNSS/INS-RTK Systems: Reasons and Analysis

This paper demonstrates the weakness of GNSS/INS-RTK (GIR) systems in mapping challenging environments because of obstruction and deflection of satellite signals. Thus, it emphasizes that the strategy of mapping companies to commercially provide maps using expensive GIR systems does not always work robustly. This limits the scalability of autonomous vehicle deployment in many road structures and modern cities. Accordingly, different critical environments in Tokyo have been analyzed and investigated to demonstrate the effects of the road structure complexity on the GIR map quality with highlighting the relevant reasons. Therefore, this paper is intended to be a reference to prove that the data of GIR systems cannot always be considered as ground truth and the integration of SLAM technologies into the mapping modules is very necessary to enable the levels four and five of autonomous driving.

LIDAR-Inertial Real-Time State Estimator with Rod-Shaped and Planar Feature

State estimation and mapping based on Light Detection and Ranging (LIDAR) are important for autonomous systems. Point cloud registration is a crucial module affecting the accuracy and real-time performance of LIDAR simultaneous localization and mapping (SLAM). In this paper, a novel point cloud feature selection for LIDAR-inertial tightly coupled systems is proposed. In the front-end, a point cloud registration is carried out after marking rod-shaped and planar feature information which is different from the existing LIDAR and inertial measurement unit (IMU) integration scheme. This preprocessing method subsequently reduces the outliers. IMU pre-integration outputs high-frequency result and is used to provide the initial value for LIDAR solution. In the scan-to-map module, a computationally efficient graph optimization framework is applied. Moreover, the LIDAR odometry further constrains the IMU states. In the back-end, the optimization based on sliding-window incorporates the LIDAR-inertial measurement and loop closure global constraints to reduce the cumulative error. Combining the front-end and back-end, we propose the low drift and high real-time LIDAR-inertial positioning system. Furthermore, we conducted an exhaustive comparison in open data sequences and real-word experiments. The proposed system outperforms much higher positioning accuracy than the state-of-the-art methods in various scenarios. Compared with the LIO-SAM, the absolute trajectory error (ATE) average RMSE (Root Mean Square Error) in this study increases by 64.45% in M2DGR street dataset (street_01, 04, 07, 10) and 24.85% in our actual scene datasets. In the most time-consuming mapping module of each system, our system runtime can also be significantly reduced due to the front-end preprocessing and back-end graph model.

Hybrid fiber–THz fronthaul supporting up to 16384-QAM-OFDM with the delta-sigma modulation

With the progress of high-capacity radio access networks, ultra-dense small cells are rapidly being deployed in urban areas. As a result, the deployment of a large number of optical fibers in urban areas becomes a severe issue. In this Letter, we propose a hybrid fiber–terahertz (THz) mobile fronthaul system supporting flexible and high-order wireless signal transmission with the delta-sigma modulation. The photonic THz transmission is used as the seamless extension of fiber-based fronthaul in small cells. A 20-Gbit/s digital fiber–THz fronthaul system is experimentally demonstrated to validate the proposed scheme, with 10-km optical fiber transmission and 300-GHz wireless relay. Carrier aggregation of up to 10 40-MHz and 60-MHz 5G-new radio (5G-NR) channels at the radio carrier frequency of 3.9 GHz is reported. The design of quantization noise suppressed delta-sigma modulation enables the system to transmit orthogonal frequency division multiplexing (OFDM) modulation up to 16384 order quadrate amplitude modulation (QAM) mapping with the error vector magnitude (EVM) below 0.5%.

Domain Adaptation on Multiple Cloud Recognition From Different Types of Meteorological Satellite

Meteorological satellites have become an indispensable meteorological tool for earth observation, as aiding in areas such as cloud detection, which has important guiding significance for maritime activities. However, it is time-consuming and labor-intensive to obtain fine-grained annotations provided by artificial experience or mature satellite cloud products for multi-spectral maritime cloud imageries, especially when new satellites are launched. Moreover, due to the data discrepancy caused by different detection bands, existing models have inadequate generalization performance compared to new satellites, and some cannot be directly migrated. In this paper, to reduce the data distribution’s discrepancy, an approach is presented based on unsupervised domain adaption method for marine cloud detection task based on Himawari-8 satellite data as a source domain and Fengyun-4 satellite data as a target domain. The goal of the proposed method is to leverage the representation power of adversarial learning to extract domain-invariant features, consisting of a segmentation model, a feature extract model for target domain, and a domain discriminator. In addition, aiming to remedy the discrepancy of detection bands, a band mapping module is designed to implement consistency between different bands. The result of the experiments demonstrated the effectiveness of the proposed method with a 7% improvement compared with the comparative experiment. We also designed a series of statistical experiments on different satellite data to further study cloudy perception representation, including data visualization experiment and cloud type statistics.

Dynamic proximal unrolling network for compressive imaging

Compressive imaging aims to recover a latent image from under-sampled measurements, suffering from a serious ill-posed inverse problem. Recently, deep neural networks have been applied to this problem with superior results, owing to the learned advanced image priors. These approaches, however, require training separate models for different imaging modalities and sampling ratios, leading to overfitting to specific settings. In this paper, a dynamic proximal unrolling network (dubbed DPUNet) was proposed, which can handle a variety of measurement matrices via one single model without retraining. Specifically, DPUNet can exploit both the embedded observation model via gradient descent and imposed image priors by learned dynamic proximal operators, achieving joint reconstruction. A key component of DPUNet is a dynamic proximal mapping module, whose parameters can be dynamically adjusted at the inference stage and make it adapt to different imaging settings. Moreover, in order to eliminate the image blocking artifacts, an enhanced version DPUNet+ is developed, which integrates a dynamic deblocking module and reconstructs jointly with DPUNet to further improve the performance. Experimental results demonstrate that the proposed method can effectively handle multiple compressive imaging modalities under varying sampling ratios and noise levels via only one trained model, and outperform the state-of-the-art approaches. Our code is available at https://github.com/Yixiao-Yang/DPUNet-PyTorch.

Peculiarities of incommensurate modulation behavior during superstructure creation in case of potential symmetry n = 4

Type or paste your abstract here as prescribed by the journal’s instructions for authors. Type or paste your abstract here as prescribed by the journal’s instructions for authors. Type or paste your abstract here as prescribed by the journal’s instructions for authors. Type or paste your abstract here. This paper deals with dynamics of incommensurate superstructure at the moment of its formation. Lyapunov exponent value spectra, phase portraits, incommensurate modulation wave vector behavior, Fourier spectra and maps of incommensurate phase dynamic modes under changed parameters of long-range interaction (Т) and anisotropic interaction (K) in interval 0.0 ÷ 1.0 were analyzed. The calculations were made in Python environment applying Skipy, JiTCODE libraries. Under low values of Т and K parameters (0.0015 ÷ 0.03) a chaotic state occurs in this system. It is determined by the interaction between different spatial areas of the correlated motion of tetrahedral groups. The interaction of spatial areas of the correlated motion of tetrahedral groups violates the modulation pattern of tetrahedral group motion causing the superstructure chaotic state. The study of Fourier spectra has shown that interaction of spatial areas of tetrahedral group correlated motion of causes the chaotic state that is non-stable and is destroyed by long-range interaction. The impact of surface energy on the interaction of spatial areas of tetrahedral group correlated motion is determined by decreased amplitude of vibrations of tetrahedral groups causing the disappearance of the chaotic state.

A 2D hydrodynamic model-based method for efficient flood inundation modelling

AbstractEfficient and accurate flood inundation predictions can provide useful information for flood risk mitigation and water resource management. In this paper, we propose a new modelling method, LoHy + , which can be applied to efficiently simulate the spatiotemporal evolution of flood inundation with reasonable accuracy. The method integrates a low-fidelity two-dimensional (2D) hydrodynamic model and a mapping module to estimate water depth in a catchment during floods. The performance of the proposed modelling method was evaluated using a real-world catchment of approximate 2,000 km2, in the Southern Murray–Darling Basin, Australia. The results show that there is a good agreement between flood inundation obtained from the proposed method and that simulated using a high-fidelity 2D hydrodynamic model. The proposed method is much more efficient than the high-fidelity 2D hydrodynamic model, which makes it an alternative method for applications requiring many model runs or long simulation durations. Also, the LoHy+ model has the potential to be applied in flood inundation forecast, flood risk mitigation design water resource management, etc.

The space of barcode bases for persistence modules

The barcode of a persistence module serves as a complete combinatorial invariant of its isomorphism class. Barcodes are typically extracted by performing changes of basis on a persistence module until the constituent matrices have a special form. Here we describe a new algorithm for computing barcodes which also keeps track of, and outputs, such a change of basis. Our main result is an explicit characterisation of the group of transformations that sends one barcode basis to another. Armed with knowledge of the entire space of barcode bases, we are able to show that any map of persistence modules can be represented via a partial matching between bars provided that neither source nor target admits nested bars in its barcode. We also generalise the algorithm and results described above to work for zizag modules.

Satellite Image for Cloud and Snow Recognition Based on Lightweight Feature Map Attention Network

Cloud and snow recognition technology is of great significance in the field of meteorology, and is also widely used in remote sensing mapping, aerospace, and other fields. Based on the traditional method of manually labeling cloud-snow areas, a method of labeling cloud and snow areas using deep learning technology has been gradually developed to improve the accuracy and efficiency of recognition. In this paper, from the perspective of designing an efficient and lightweight network model, a cloud snow recognition model based on a lightweight feature map attention network (Lw-fmaNet) is proposed to ensure the performance and accuracy of the cloud snow recognition model. The model is improved based on the ResNet18 network with the premise of reducing the network parameters and improving the training efficiency. The main structure of the model includes a shallow feature extraction module, an intrinsic feature mapping module, and a lightweight adaptive attention mechanism. Overall, in the experiments conducted in this paper, the accuracy of the proposed cloud and snow recognition model reaches 95.02%, with a Kappa index of 93.34%. The proposed method achieves an average precision rate of 94.87%, an average recall rate of 94.79%, and an average F1-Score of 94.82% for four sample recognition classification tasks: no snow and no clouds, thin cloud, thick cloud, and snow cover. Meanwhile, our proposed network has only 5.617M parameters and takes only 2.276 s. Compared with multiple convolutional neural networks and lightweight networks commonly used for cloud and snow recognition, our proposed lightweight feature map attention network has a better performance when it comes to performing cloud and snow recognition tasks.

Diagnosis of exercise-induced cardiac fatigue based on deep learning and heart sounds

Exercised-induced cardiac fatigue (EICF) refers to an impermanent decline in systolic and diastolic function caused by high-intensity and multi-frequency exercise. Long-term EICF may lead to heart fatigue, myocardial damage, and even sudden cardiac death. However, common cardiac fatigue diagnoses rely on expensive devices or time. Further, cardiac inotropy as an essential reference has not been applied to measure cardiac fatigue. In this paper, heart sound was proposed to evaluate EICF based on its ability to reflect changes of cardiac contractility, with a specialized deep learning network designed to recognize subjects with EICF. First, heart sounds were collected by a physiological signal collection system, and a heart sound database for 20 subjects was established. Then, discrete wavelet transform and logistic regression hidden semi-Markov model were applied to denoise and segment signals respectively, and 1770 samples in total were obtained. Finally, a network unifying residual mapping and attention modules was designed to recognize heart sounds, and the accuracy, precision, and recall of the model were 98.85%, 98.94%, and 98.9% respectively. This study suggests that heart sounds combined with the deep learning model can achieve accurate and objective diagnosis, which is potential for a reliable alternative to diagnose EICF.

EV-VINS: An Efficient and Versatile Binocular Visual-Inertial SLAM Algorithm

To address the problem that the current optimization-based visual-inertial SLAM algorithms have difficulty in achieving high accuracy, high robustness and high efficiency at the same time, an efficient and versatile SLAM algorithm (EV-VINS) based on the improvement of VINS-Mono is proposed in this paper. EV-VINS tightly coupling the binocular and inertial measurement unit is divided into decoupled front-end, which detects GFTT corners and performs optical flow tracking, and back-end, which mainly performs initialization, nonlinear optimization and outlier rejection. The dense map module is added for subsequent navigation functions. In particular, a feature classification strategy is proposed based on the analysis of the existing problems in the initialization, which not only greatly reduces the number of outliers during initialization, but also makes the points used for back-end optimization have good initial values. Therefore, the computational efficiency and the stability of the back-end optimization are significantly improved while ensuring the accuracy. The simulation experiments based on the EuRoC datasets and actual test results show that EV-VINS has better real-time performance while having the basically same location accuracy compared to the classical algorithms.

SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-resolution

In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline is redundant and inefficient for the independent processes, and some inner features could have been shared. Therefore, we present an efficient paradigm to perform Simultaneously Image Colorization and Super-resolution (SCS) and propose an end-to-end SCSNet to achieve this goal. The proposed method consists of two parts: colorization branch for learning color information that employs the proposed plug-and-play Pyramid Valve Cross Attention (PVCAttn) module to aggregate feature maps between source and reference images; and super-resolution branch for integrating color and texture information to predict target images, which uses the designed Continuous Pixel Mapping (CPM) module to predict high-resolution images at continuous magnification. Furthermore, our SCSNet supports both automatic and referential modes that is more flexible for practical application. Abundant experiments demonstrate the superiority of our method for generating authentic images over state-of-the-art methods, e.g., averagely decreasing FID by 1.8 and 5.1 compared with current best scores for automatic and referential modes, respectively, while owning fewer parameters (more than x2) and faster running speed (more than x3).