Search

A high-quality land-use dataset is crucial for constructing a high-performance land-use classification model. Due to the complexity and spatial heterogeneity of land-use, the dataset construction process is inefficient and costly. This challenge affects the quality of datasets, consequently impacting the model's performance. The emerging field of Data-Centric Artificial Intelligence (DCAI) is expected to deliver techniques for dataset optimization, offering a promising solution to the problem. Therefore, this study proposes a data-centric framework named DCAI-CLUD for the construction of land-use datasets. Based on this framework, the accuracy and rate of data labeling are improved by 5.93 and 28.97%. The Gini index of the dataset and the proportion of samples with non-mixed land-use categories are enhanced by 3.27 and 8.52%. The overall accuracy (OA) and Kappa of the land-use classification model improved significantly by 27.87 and 58.08%. This study is the first to introduce DCAI into the field of geographic information and remote sensing and verify its effectiveness. The proposed framework can effectively improve the construction efficiency and quality of the dataset and synchronously optimize the model performance. Based on the proposed framework, we constructed a multi-source land-use dataset of major cities in China named CN-MSLU-100K. HIGHLIGHTS: A framework for optimizing the land-use dataset construction process is proposed. Filtering and pre-labeling improved the quality and efficiency of data labeling. The performance of land-use classification model is enhanced by dataset optimization. Preconceived results have a subjective impact on the data labelers. The first study to introduce DCAI for land-use classification is launched. [ABSTRACT FROM AUTHOR]

Copyright of Journal of South-Central Minzu University (Natural Science Edition) is the property of Journal of South-Central Minzu University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Restoring a high-resolution (HR) image from a low-resolution (LR) image using deep learning (DL) techniques is becoming a popular restoration approach in the remote sensing image super-resolution (SR). However, blurry object edges, artifacts, memory usage, and computational burdens are still challenges in remote sensing image SR. To overcome these challenges, a lightweight Multiwavelet-based Multiscale Dilated Attention Network (MMDAN) for remote-sensing image SR is proposed. The main aim of the proposed work is to reconstruct the HR image in the multiwavelet domain. The SR scheme based on the multiwavelets is proposed under a DL framework to exploit the contextual information from sixteen subbands of multiwavelets. A multiscale dilated convolution, along with a nested attention module, is employed as a deep feature extraction function to enhance the image restoration of the proposed model. Experiments on remote sensing and natural image datasets show the superiority of the proposed model in resolution enhancement. [ABSTRACT FROM AUTHOR]

The multi-scale representation of remote sensing images is crucial for information extraction, data analysis, and image processing. However, traditional methods such as image pyramid and image filtering often result in the loss of image details, particularly edge information, during the simplification and merging processes at different scales and resolutions. Furthermore, when applied to coastal landforms with rich texture features, such as biologically diverse areas covered with vegetation, these methods struggle to preserve the original texture characteristics. In this study, we propose a new method, multi-scale expression of coastal landforms considering texture features (METF-C), based on computer vision techniques. This method combines superpixel segmentation and texture transfer technology to improve the multi-scale representation of coastal landforms in remote sensing images. First, coastal landform elements are segmented using superpixel technology. Then, global merging is performed by selecting different classes of superpixels, with boundaries smoothed using median filtering and morphological operators. Finally, texture transfer is applied to create a fusion image that maintains both scale and level consistency. Experimental results demonstrate that METF-C outperforms traditional methods by effectively simplifying images while preserving important geomorphic features and maintaining global texture information across multiple scales. This approach offers significant improvements in edge preservation and texture retention, making it a valuable tool for analyzing coastal landforms in remote sensing imagery. [ABSTRACT FROM AUTHOR]

Achieving precise and swift monitoring of aquaculture ponds in coastal regions is essential for the scientific planning of spatial layouts in aquaculture zones and the advancement of ecological sustainability in coastal areas. However, because the distribution of many land types in coastal areas and the complex spectral features of remote sensing images are prone to the phenomenon of 'same spectrum heterogeneous objects', the current deep learning model is susceptible to background noise interference in the face of complex backgrounds, resulting in poor model generalization ability. Moreover, with the image features of aquaculture ponds of different scales, the model has limited multi-scale feature extraction ability, making it difficult to extract effective edge features. To address these issues, this work suggests a novel semantic segmentation model for aquaculture ponds called MPG-Net, which is based on an enhanced version of the U-Net model and primarily comprises two structures: MS and PGC. The MS structure integrates the Inception module and the Dilated residual module in order to enhance the model's ability to extract the features of aquaculture ponds and effectively solve the problem of gradient disappearance in the training of the model; the PGC structure integrates the Global Context module and the Polarized Self-Attention in order to enhance the model's ability to understand the contextual semantic information and reduce the interference of redundant information. Using Sentinel-2 and Planet images as data sources, the effectiveness of the refined method is confirmed through ablation experiments conducted on the two structures. The experimental comparison using the FCN8S, SegNet, U-Net, and DeepLabV3 classical semantic segmentation models shows that the MPG-Net model outperforms the other four models in all four precision evaluation indicators; the average values of precision, recall, IoU, and F1-Score of the two image datasets with different resolutions are 94.95%, 92.95%, 88.57%, and 93.94%, respectively. These values prove that the MPG-Net model has better robustness and generalization ability, which can reduce the interference of irrelevant information, effectively improve the extraction precision of individual aquaculture ponds, and significantly reduce the edge adhesion of aquaculture ponds in the extraction results, thereby offering new technical support for the automatic extraction of aquaculture ponds in coastal areas. [ABSTRACT FROM AUTHOR]

ABSTRACT Most existing remote sensing image watermarking algorithms concentrate on excavation of particular embedding templates, image features, or geometric invariant domains, which present challenges in terms of resistance to desynchronization attacks, embedding domain repetition, and insufficient algorithm versatility. To address these issues, this study proposes a watermarking algorithm that is robust to desynchronization attacks and can adapt to different types of remote sensing images using the geometric invariant domain and hybrid frequency domain. The algorithm uses the multi‐scale SIFT to identify feature points in remote sensing images, then creates a Delaunay triangulation network (DTN) based on these feature points, extracts the tangent circles of triangles, and normalizes these tangent circles using image moment and affine transformation, and the feature domains with geometric invariance are constructed. On this basis, the discrete wavelet transform (DWT) transforms the feature domain to the frequency decomposition state, and the singular value decomposition (SVD) further mines the watermark embedding domain, ensuring the stability of the watermark transforming back and forth in the embedding domain and improving the overall invisibility of the watermarking algorithm. The experimental results indicate that, compared to related algorithms, the proposed watermarking algorithm not only adapts better to remote sensing images with different bands and bit depths but also provides superior invisibility and demonstrates strong robustness against various desynchronization attacks such as splicing, panning, rotating, as well as image processing like noise addition, filtering, and compression. [ABSTRACT FROM AUTHOR]

As one of the major global food crops, the monitoring and management of the winter wheat planting area is of great significance for agricultural production and food security worldwide. Today, the development of high-resolution remote sensing imaging technology has provided rich sources of data for extracting the visual planting information of winter wheat. However, the existing research mostly focuses on extracting the planting plots that have a simple terrain structure. In the face of diverse terrain features combining mountainous areas, plains, and saline alkali land, as well as small-scale but complex planting structures, the extraction of planting plots through remote sensing imaging is subjected to great challenges in terms of recognition accuracy and model complexity. In this paper, we propose a modified Segformer model for extracting winter wheat planting plots with complex structures in rural areas based on the 0.8 m high-resolution multispectral data obtained from the Gaofen-2 satellite, which significantly improves the extraction accuracy and efficiency under complex conditions. In the encoder and decoder of this method, new modules were developed for the purpose of optimizing the feature extraction and fusion process. Specifically, the improvement measures of the proposed method include: (1) The MixFFN module in the original Segformer model is replaced with the Multi-Scale Feature Fusion Fully-connected Network (MSF-FFN) module, which enhances the model's representation ability in handling complex terrain features through multi-scale feature extraction and position embedding convolution; furthermore, the DropPath mechanism is introduced to reduce the possibility of overfitting while improving the model's generalization ability. (2) In the decoder part, after fusing features at four different scales, a CoordAttention module is added, which can precisely locate important regions with enhanced features in the images by utilizing the coordinate attention mechanism, therefore further improving the model's extraction accuracy. (3) The model's input data are strengthened by incorporating multispectral indices, which are also conducive to the improvement of the overall extraction accuracy. The experimental results show that the accuracy rate of the modified Segformer model in extracting winter wheat planting plots is significantly increased compared to traditional segmentation models, with the mean Intersection over Union (mIOU) and mean Pixel Accuracy (mPA) reaching 89.88% and 94.67%, respectively (an increase of 1.93 and 1.23 percentage points, respectively, compared to the baseline model). Meanwhile, the parameter count and computational complexity are significantly reduced compared to other similar models. Furthermore, when multispectral indices are input into the model, the mIOU and mPA reach 90.97% and 95.16%, respectively (an increase of 3.02 and 1.72 percentage points, respectively, compared to the baseline model). [ABSTRACT FROM AUTHOR]

Online maps are of great importance in modern life, especially in commuting, traveling and urban planning. The accessibility of remote sensing (RS) images has contributed to the widespread practice of generating online maps based on RS images. The previous works leverage an idea of domain mapping to achieve end-to-end remote sensing image-to-map translation (RSMT). Although existing methods are effective and efficient for online map generation, generated online maps still suffer from ground features distortion and boundary inaccuracy to a certain extent. Recently, the emergence of diffusion models has signaled a significant advance in high-fidelity image synthesis. Based on rigorous mathematical theories, denoising diffusion models can offer controllable generation in sampling process, which are very suitable for end-to-end RSMT. Therefore, we design a novel end-to-end diffusion model to generate online maps directly from remote sensing images, called MapGen-Diff. We leverage a strategy inspired by Brownian motion to make a trade-off between the diversity and the accuracy of generation process. Meanwhile, an image compression module is proposed to map the raw images into the latent space for capturing more perception features. In order to enhance the geometric accuracy of ground features, a consistency regularization is designed, which allows the model to generate maps with clearer boundaries and colorization. Compared to several state-of-the-art methods, the proposed MapGen-Diff achieves outstanding performance, especially a 5 % RMSE and 7 % SSIM improvement on Los Angeles and Toronto datasets. The visualization results also demonstrate more accurate local details and higher quality. [ABSTRACT FROM AUTHOR]

Identifying ships is essential for maritime situational awareness. Automatic identification system (AIS) data and remote sensing (RS) images provide information on ship movement and properties from different perspectives. This study develops an efficient spatiotemporal association approach that combines AIS data and RS images for point–track association. Ship detection and feature extraction from the RS images are performed using deep learning. The detected image characteristics and neighboring AIS data are compared using a multi-dimensional feature similarity model that considers similarities in space, time, course, and attributes. An efficient spatial–temporal association analysis of ships in RS images and AIS data is achieved using the interval type-2 fuzzy system (IT2FS) method. Finally, optical images with different resolutions and AIS records near the waters of Yokosuka Port and Kure are collected to test the proposed model. The results show that compared with the multi-factor fuzzy comprehensive decision-making method, the proposed method can achieve the best performance (F1 scores of 0.7302 and 0.9189, respectively, on GF1 and GF2 images) while maintaining a specific efficiency. This work can realize ship positioning and monitoring based on multi-source data and enhance maritime situational awareness. [ABSTRACT FROM AUTHOR]

Land image recognition and classification and land environment detection are important research fields in remote sensing applications. Because of the diversity and complexity of different tasks of land environment recognition and classification, it is difficult for researchers to use a single model to achieve the best performance in scene classification of multiple remote sensing land images. Therefore, to determine which model is the best for the current recognition classification tasks, it is often necessary to select and experiment with many different models. However, finding the optimal model is accompanied by an increase in trial-and-error costs and is a waste of researchers' time, and it is often impossible to find the right model quickly. To address the issue of existing models being too large for easy selection, this paper proposes a multi-path reconfigurable network structure and takes the multi-path reconfigurable residual network (MR-ResNet) model as an example. The reconfigurable neural network model allows researchers to selectively choose the required modules and reassemble them to generate customized models by splitting the trained models and connecting them through modules with different properties. At the same time, by introducing the concept of a multi-path input network, the optimal path is selected by inputting different modules, which shortens the training time of the model and allows researchers to easily find the network model suitable for the current application scenario. A lot of training data, computational resources, and model parameter experience are saved. Three public datasets, NWPU-RESISC45, RSSCN7, and SIRI-WHU datasets, were used for the experiments. The experimental results demonstrate that the proposed model surpasses the classic residual network (ResNet) in terms of both parameters and performance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Remote sensing image scene classification (RSISC) greatly benefits from the use of few-shot learning, as it enables the recognition of novel scenes with only a small amount of labeled data. Most previous works focused on learning representations of prior knowledge with scarce labeled data while ignoring the feasibility of using potential information with large amounts of unlabeled data. In this paper, we introduce a novel semi-supervised few-shot pseudo-label propagation method through the introduction of unlabeled knowledge. This approach utilizes the pseudo-loss property generated by the classifier to indirectly reflect the credibility of pseudo-labeled samples. Therefore, we propose a semi-supervised pseudo-loss confidence metric-based method called a pseudolabel meta-learner (PLML) for RSISC. Specifically, we adopt a pseudoloss estimation module to map the pseudo-labeled data obtained from different tasks to a unified pseudo-loss metric space. Then, the distributions of the pseudolosses with both correct and incorrect pseudolabels are fitted by a semi-supervised beta mixture model (ss-BMM). This model can iteratively select high-quality unlabeled data to enhance the self-training effect of the classifier. Finally, to address the problem of shifting pseudo-loss distributions in remote sensing images, a progressive self-training strategy is proposed to mitigate the cumulative error induced by the classifier. Experimental results demonstrate that our proposed PLML approach outperforms the existing alternatives on the NWPU-RESISC45, AID, and UC Merced datasets. [ABSTRACT FROM AUTHOR]

In this paper, a new spatiotemporal chaos model is proposed to improve the security and anti-decryption capability of remote sensing image encryption algorithm. The model is the Hash Arnold Coupled Logistic Map Lattices (HACLML) based on the Arnold Coupled Logistic Map Lattices (ACLML). By introducing hash index chain mapping, the chaotic performance of ACLML is improved significantly. Then, a novel image encryption algorithm is obtained based on the HACLML. In the scrambling stage, a point-to-block encryption method is designed to make the correlation between image pixels fully scrambled. In addition, according to the structure of HACLML and double hash index chain, a diffusion encryption algorithm is designed to further enhance the security of the encrypted image. The security analysis experiments show that the image encryption algorithm based on the HACLML has significant advantages in security, and is suitable for the practical application scenarios such as remote sensing images with high security requirements. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Few-shot segmentation aims to segment objects in a task dataset with only a few labelled target examples, aided by a lot of labelled auxiliary datasets. Existing approaches typically assume that the task dataset and auxiliary dataset originate from the same source but have disjoint category sets. However, it is common in remote sensing image segmentation tasks that the datasets are from different sources and the category sets are often partially overlapped, where models trained on the auxiliary dataset degrade in performance on the task dataset. To address these issues, we present a few-shot segmentation method based on graph network and open-set domain adaptation. The proposed method utilizes a graph model to capture the relationships between super pixels and to predict labels for the unlabelled samples by label propagation, meanwhile, leverages open-set domain adaptation to reduce inter-domain discrepancies and enhances model transferability. The proposed method is evaluated on two publicly available datasets, and the effectiveness of the proposed approach is demonstrated by the significant improvement in accuracy compared to existing methods. [ABSTRACT FROM AUTHOR]

With the rapid development of remote sensing image data, the efficient retrieval of target images of interest has become an important issue in various applications including computer vision and remote sensing. This research addressed the low-accuracy problem in traditional content-based image retrieval algorithms, which largely rely on comparing entire image features without capturing sufficient semantic information. We proposed a scene graph similarity-based remote sensing image retrieval algorithm. Firstly, a one-shot object detection algorithm was designed for remote sensing images based on Siamese networks and tailored to the objects of an unknown class in the query image. Secondly, a scene graph construction algorithm was developed, based on the objects and their attributes and spatial relationships. Several construction strategies were designed based on different relationships, including full connections, random connections, nearest connections, star connections, or ring connections. Thirdly, by making full use of edge features for scene graph feature extraction, a graph feature extraction network was established based on edge features. Fourthly, a neural tensor network-based similarity calculation algorithm was designed for graph feature vectors to obtain image retrieval results. Fifthly, a dataset named remote sensing images with scene graphs (RSSG) was built for testing, which contained 929 remote sensing images with their corresponding scene graphs generated by the developed construction strategies. Finally, through performance comparison experiments with remote sensing image retrieval algorithms AMFMN, MiLaN, and AHCL, in precision rates, Precision@1 improved by 10%, 7.2%, and 5.2%, Precision@5 improved by 3%, 5%, and 1.7%; and Precision@10 improved by 1.7%, 3%, and 0.6%. In recall rates, Recall@1 improved by 2.5%, 4.3%, and 1.3%; Recall@5 improved by 3.7%, 6.2%, and 2.1%; and Recall@10 improved by 4.4%, 7.7% and 1.6%. [ABSTRACT FROM AUTHOR]

Satellite remote sensing images, obtained through imaging earth from space, are widely used in military and national economic construction. Remote sensing images of sea-related scenes usually contain important military-sensitive information, so there is a risk of information leakage during data transmission. To enhance image security, an optical remote sensing image encryption algorithm is proposed for sensitive targets in sea-related scenarios. The proposed method is divided into two main components: object detection and image encryption. This method first utilizes YOLOv7 for object detection and then selectively encrypts the image by scrambling pixels across three planes and diffusing them cross-plane. A novel chaotic map for generating encryption sequences is also proposed, which combines a discrete Grunwald–Letnikov fractional-order memristor and classical sine map. The simulation results demonstrate the effectiveness of the proposed method and its ability to resist chosen plaintext attack. [ABSTRACT FROM AUTHOR]

Advances in deep learning and computer vision techniques have made impacts in the field of remote sensing, enabling efficient data analysis for applications such as land cover classification and change detection. Convolutional neural networks (CNNs) and transformer architectures have been utilized in visual perception algorithms due to their effectiveness in analyzing local features and global context. In this paper, we propose a hybrid transformer architecture that consists of a CNN-based encoder and transformer-based decoder. We propose a feature adjustment module that refines the multiscale feature maps extracted from an EfficientNet backbone network. The adjusted feature maps are integrated into the transformer-based decoder to perform the semantic segmentation of the remote sensing images. This paper refers to the proposed encoder–decoder architecture as a semantic feature adjustment network (SFA-Net). To demonstrate the effectiveness of the SFA-Net, experiments were thoroughly conducted with four public benchmark datasets, including the UAVid, ISPRS Potsdam, ISPRS Vaihingen, and LoveDA datasets. The proposed model achieved state-of-the-art accuracy on the UAVid, ISPRS Vaihingen, and LoveDA datasets for the segmentation of the remote sensing images. On the ISPRS Potsdam dataset, our method achieved comparable accuracy to the latest model while reducing the number of trainable parameters from 113.8 M to 10.7 M. [ABSTRACT FROM AUTHOR]

Copyright of World Nuclear Geoscience is the property of World Nuclear Geoscience Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Urban Geology is the property of Urban Geology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Remote Sensing for Natural Resources is the property of Remote Sensing for Natural Resources Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Remote Sensing for Natural Resources is the property of Remote Sensing for Natural Resources Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The degradation of optical remote sensing images due to atmospheric haze poses a significant obstacle, profoundly impeding their effective utilization across various domains. Dehazing methodologies have emerged as pivotal components of image preprocessing, fostering an improvement in the quality of remote sensing imagery. This enhancement renders remote sensing data more indispensable, thereby enhancing the accuracy of target identification. Conventional defogging techniques based on simplistic atmospheric degradation models have proven inadequate for mitigating non-uniform haze within remotely sensed images. In response to this challenge, a novel UNet Residual Attention Network (URA-Net) is proposed. This paradigmatic approach materializes as an end-to-end convolutional neural network distinguished by its utilization of multi-scale dense feature fusion clusters and gated jump connections. The essence of our methodology lies in local feature fusion within dense residual clusters, enabling the extraction of pertinent features from both preceding and current local data, depending on contextual demands. The intelligently orchestrated gated structures facilitate the propagation of these features to the decoder, resulting in superior outcomes in haze removal. Empirical validation through a plethora of experiments substantiates the efficacy of URA-Net, demonstrating its superior performance compared to existing methods when applied to established datasets for remote sensing image defogging. On the RICE-1 dataset, URA-Net achieves a Peak Signal-to-Noise Ratio (PSNR) of 29.07 dB, surpassing the Dark Channel Prior (DCP) by 11.17 dB, the All-in-One Network for Dehazing (AOD) by 7.82 dB, the Optimal Transmission Map and Adaptive Atmospheric Light For Dehazing (OTM-AAL) by 5.37 dB, the Unsupervised Single Image Dehazing (USID) by 8.0 dB, and the Superpixel-based Remote Sensing Image Dehazing (SRD) by 8.5 dB. Particularly noteworthy, on the SateHaze1k dataset, URA-Net attains preeminence in overall performance, yielding defogged images characterized by consistent visual quality. This underscores the contribution of the research to the advancement of remote sensing technology, providing a robust and efficient solution for alleviating the adverse effects of haze on image quality. Graphic Abstract [ABSTRACT FROM AUTHOR]

Oriented object detection has garnered significant attention for its broad applications in remote sensing image processing. Most oriented detectors perform dense predictions on a set of predefined anchors to generate oriented bounding boxes, where these anchors require classification (cls) and localization (loc) labels for detector training. Recent advancements in label assignment utilize the overall quality score of cls and loc predictions to determine positive and negative samples for each oriented object. However, these methods typically establish the overall quality score by assigning fixed weights to cls and loc quality scores. This approach may not be optimal, as fixed weights fail to dynamically balance cls and loc performance during model optimization, thereby constraining detection efficacy. Motivated by this observation, this paper proposes a Dynamic Weighting Label Assignment (DWLA) algorithm. DWLA dynamically adjusts the weights of individual quality scores based on the current model state to continuously balance cls and loc performance. Additionally, to mitigate the impact of unreliable predictions and achieve more stable training, this paper proposes a level-wise positive sample selection scheme and an object-adaptive scheme for constructing initial candidates of positive samples, respectively. Comprehensive experiments on the DOTA and UCAS-AOD datasets have validated the effectiveness of the proposed DWLA. [ABSTRACT FROM AUTHOR]

In the realm of urban planning and environmental evaluation, the delineation and categorization of land types are pivotal. This study introduces a convolutional neural network-based image semantic segmentation approach to delineate parcel data in remote sensing imagery. The initial phase involved a comparative analysis of various CNN architectures. ResNet and VGG serve as the foundational networks for training, followed by a comparative assessment of the experimental outcomes. Subsequently, the VGG+U-Net model, which demonstrated superior efficacy, was chosen as the primary network. Enhancements to this model were made by integrating attention mechanisms. Specifically, three distinct attention mechanisms—spatial, SE, and channel—were incorporated into the VGG+U-Net framework, and various loss functions were evaluated and selected. The impact of these attention mechanisms, in conjunction with different loss functions, was scrutinized. This study proposes a novel network model, designated VGG+U-Net+Channel, that leverages the VGG architecture as the backbone network in conjunction with the U-Net structure and augments it with the channel attention mechanism to refine the model's performance. This refinement resulted in a 1.14% enhancement in the network's overall precision and marked improvements in MPA and MioU. A comparative analysis of the detection capabilities between the enhanced and original models was conducted, including a pixel count for each category to ascertain the extent of various semantic information. The experimental validation confirms the viability and efficacy of the proposed methodology. [ABSTRACT FROM AUTHOR]

Building segmentation in high resolution remote sensing images is one of the hotspots in remote sensing image research. The diversity of building scales in high-resolution remote sensing images easily leads to wrong segmentation, missing segmentation and fuzzy boundaries. In order to solve the above problems, this paper proposes a remote sensing building image segmentation network based on U-Net network structure with double coder U-shaped network (DCU-Net). DCU-Net adds a parallel coding path to U-Net to form a dual-path coding structure. Dense residual coding module (DRCM) and multi-scale dilated convolutional coding module (MDCCM) are designed in the encoding stage to enhance multi-scale feature extraction. The dual hybrid attention module (DFAM) is added to the network to enhance the expression ability of the network for features. In order to verify the effectiveness of the network, experiments are carried out on WHU and Massachusetts datasets. The recall, F1 and intersection over union ratio indicators reach 91.26%, 92.33% and 86.15% on WHU dataset, and reach 81.64%, 84.33% and 82.72% on Massachusetts Buildings dataset. The results show that DCU-Net has high extraction accuracy for building extraction at different scales.

Abstract Remote Sensing Image Object Detection (RSIOD) faces the challenges of multi-scale objects, dense overlap of objects and uneven data distribution in practical applications. In order to solve these problems, this paper proposes a YOLO-ACPHD RSIOD algorithm. The algorithm adopts Adaptive Condition Awareness Technology (ACAT), which can dynamically adjust the parameters of the convolution kernel, so as to adapt to the objects of different scales and positions. Compared with the traditional fixed convolution kernel, this dynamic adjustment can better adapt to the diversity of scale, direction and shape of the object, thus improving the accuracy and robustness of Object Detection (OD). In addition, a High-Dimensional Decoupling Technology (HDDT) is used to reduce the amount of calculation to 1/N by performing deep convolution on the input data and then performing spatial convolution on each channel. When dealing with large-scale Remote Sensing Image (RSI) data, this reduction in computation can significantly improve the efficiency of the algorithm and accelerate the speed of OD, so as to better adapt to the needs of practical application scenarios. Through the experimental verification of the RSOD RSI data set, the YOLO-ACPHD model in this paper shows very satisfactory performance. The F1 value reaches 0.99, the Precision value reaches 1, the Precision-Recall value reaches 0.994, the Recall value reaches 1, and the mAP value reaches 99.36 $$\%$$ % , which indicates that the model shows the highest level in the accuracy and comprehensiveness of OD.

Building use identification is crucial in urban planning and management. Current identification methods often rely on a single data source and neglect spatial proximity. In this paper, we propose a stepwise urban building use identification framework that integrates remote sensing and social sensing data with spatial constraints based on the association of buildings with Point of Interest (POI), Area of Interest (AOI) and remote sensing data. First, the study data are preprocessed using geometric correction and POI and AOI reclassification. Then, we identify buildings with the quantitative-density index of the POIs as well as the spatial relationships between the AOIs and the buildings. Next, we generate Traffic Analysis Zones (TAZs) from road network data and utilize the similarity in physical features of buildings from remote sensing data to identify building use within spatial constraints. Finally, POI kernel density estimation is used to determine the semantic features of the buildings, and the similarity of the features between the buildings is utilized to identify the remaining buildings. The specificity of our proposed framework lies not only in the combination of multiple source data at the building-level but also in the introduction of the spatial relationships of AOIs and spatial constraints. Shenyang is selected as an example. The proposed framework identifies buildings as commercial, residential, industrial, public service and scenic spots. The accuracy assessment indicates that the proposed framework performs well, with an Overall Accuracy (OA) of 87.1% and a kappa coefficient (kappa) of 73.4%. The results of the comparison experiments show that the consideration of spatial constraints and the integration of multiple data sources help to improve the accuracy of building use identification. The proposed framework provides a new tool for better identification of urban building use, and the generated data are suitable for in-depth analyses such as building-level urban heat islands.

Abstract Remote sensing image object detection is widely used in civil and military fields. The important task is to detect objects such as ships, planes, airports, harbours and so on, and then it can obtain object category and position information. It is of great significance to use remote sensing images to observe the densely arranged and directional targets such as cars and ships parked in parking lots and harbours. The object detection task mainly includes object localization and classification. Remote sensing images contain large number of small objects and dense scenes due to the long shooting distance and wide coverage. Small objects occupy few pixels in the image, and they are easily miss‐detected. In dense scenes, the overlapping part of each object is large, so it is easy to detect objects repeatedly. The traditional small object detection methods deliver low accuracy and take long time. Therefore, object detection is very challenging. We put forward a novel deep learning‐based single shot multibox detector (SSD) model for object detection. First, we propose an improved inception network to optimize SSD to strengthen the small object feature extraction ability (FEA) in the shallow network. Second, the feature pyramid network is modified to enhance the fusion effect. Third, the deep feature fusion module is designed to improve the FEA of the deep network. Finally, the extracted image features are matched with candidate boxes with different aspect ratios to perform object detection and location with different scales. Experiments on DOTA show that the proposed algorithm can adapt to the remote sensing object detection in different backgrounds, and effectively improve the detection effect of remote sensing objects in complex scenes.

Remote Sensing Image Object Detection (RSIOD) faces the challenges of multi-scale objects, dense overlap of objects and uneven data distribution in practical applications. In order to solve these problems, this paper proposes a YOLO-ACPHD RSIOD algorithm. The algorithm adopts Adaptive Condition Awareness Technology (ACAT), which can dynamically adjust the parameters of the convolution kernel, so as to adapt to the objects of different scales and positions. Compared with the traditional fixed convolution kernel, this dynamic adjustment can better adapt to the diversity of scale, direction and shape of the object, thus improving the accuracy and robustness of Object Detection (OD). In addition, a High-Dimensional Decoupling Technology (HDDT) is used to reduce the amount of calculation to 1/N by performing deep convolution on the input data and then performing spatial convolution on each channel. When dealing with large-scale Remote Sensing Image (RSI) data, this reduction in computation can significantly improve the efficiency of the algorithm and accelerate the speed of OD, so as to better adapt to the needs of practical application scenarios. Through the experimental verification of the RSOD RSI data set, the YOLO-ACPHD model in this paper shows very satisfactory performance. The F1 value reaches 0.99, the Precision value reaches 1, the Precision-Recall value reaches 0.994, the Recall value reaches 1, and the mAP value reaches 99.36 % , which indicates that the model shows the highest level in the accuracy and comprehensiveness of OD. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Mangroves are unique coastal blue carbon ecosystems in tropical and subtropical areas. However, the dynamic changes of their carbon storage are rarely reported. Based on ground sample points and WorldView-3 high-resolution remote sensing images obtained in 2017, we identified the canopy of dominant mangrove communities in Futian mangrove utilizing random forest algorithm and object-oriented classification methods, and inverted and calculated the area of each dominant community. We then calculated the carbon storage of each dominant community combining the field survey data in 2017, 2020 and 2023, and obtained the spatial distribution and interannual dynamic changes of carbon storage of mangrove communities. The results were as follows: (1) The overall accuracy of the random forest algorithm for canopy identification was 82.29%, with a Kappa coefficient of 0.77; Futian mangrove spaned an area of 93.84 hm², with Kandelia obovata having the largest distribution area of 49.96 hm², followed by Avicennia marina, Sonneratia caseolaris, S. apetala, and Bruguiera gymnorhiza, with respective areas of 26.23, 8.90, 6.52, and 0.50 hm². (2) The total carbon storage of Kandelia obovata community was the highest, followed by Avicennia marina, Sonneratia caseolaris, S. apetala, and Bruguiera gymnorhiza the lowest. The carbon density in Sonneratia apetala and S. caseolaris community showed an increasing trend, and S. apetala community revealed the highest among the five dominant communities. The carbon density of Kandelia obovata community increased first and then decreased, while Avicennia marina community showed a downward trend consistently, and carbon density in Bruguiera gymnorhiza community did not vary significantly. In summary, the carbon storage of mangrove dominant communities in Futian did not change much from 2017 to 2023. The carbon sequestration capacity of mangrove in Kandelia obovata, Sonneratia apetala and S. caseolaris communities was stronger. The carbon density of Avicennia marina community decreased year by year, while that of Bruguiera gymnorhiza community was relatively stable. These results provide foundational data for evaluating the carbon sequestration capacities of different dominant communities in Futian mangrove, in tandem with scientific support for subsequent mangrove restoration and management. [ABSTRACT FROM AUTHOR]

Given the impressive achievement of convolutional neural networks (CNNs) in grasping image priors from extensive datasets, they have been widely utilized for tasks related to image restoration. Recently, there is been significant progress in another category of neural architectures—Transformers. These models have demonstrated remarkable performance in natural language tasks and higher‐level vision applications. Despite their ability to address some of CNNs limitations, such as restricted receptive fields and adaptability issues, Transformer models often face difficulties when processing images with a high level of detail. This is because the complexity of the computations required increases significantly with the image's spatial resolution. As a result, their application to most high‐resolution image restoration tasks becomes impractical. In our research, we introduce a novel Transformer model, named DehFormer, by implementing specific design modifications in its fundamental components, for example, the multi‐head attention and feed‐forward network. Specifically, the proposed architecture consists of the three modules, that is, (a) multi‐scale feature aggregation network (MSFAN), (b) the gated‐Dconv feed‐forward network (GFFN), (c) and the multi‐Dconv head transposed attention (MDHTA). For the MDHTA module, our objective is to scrutinize the mechanics of scaled dot‐product attention through the utilization of per‐element product operations, thereby bypassing the need for matrix multiplications and operating directly in the frequency domain for enhanced efficiency. For the GFFN module, which enables only the relevant and valuable information to advance through the network hierarchy, thereby enhancing the efficiency of information flow within the model. Extensive experiments are conducted on the SateHazelk, RS‐Haze, and RSID datasets, resulting in performance that significantly exceeds that of existing methods. [ABSTRACT FROM AUTHOR]

With the continuous development and popularization of remote sensing technology, remote sensing images have been widely used in the field of land cover classification. Since remote sensing images have complex spatial structure and texture features, it is becoming a challenging problem to accurately categorize them. Land cover classification has practical application value in various fields, such as environmental monitoring and protection, urban and rural planning and management, and climate change research. In recent years, remote sensing image classification methods based on deep learning have been rapidly developed, in which semantic segmentation technology has become one of the mainstream methods for land cover classification using remote sensing image. Traditional semantic segmentation algorithms tend to ignore the edge information, resulting in poor classification of the edge part in land cover classification, and there are numerous attention mechanisms to make improvements for these problems. In this paper, a triple attention mechanism, BETAM (Border-Enhanced Triple Attention Mechanism), for edge feature enhancement of high-resolution remote sensing images is proposed. Furthermore, a new model on the basis of the semantic segmentation network model DeeplabV3+ is also introduced, which is called DeepBETAM. The triple attention mechanism BETAM is able to capture feature dependencies in three dimensions: position, space, and channel, respectively. Through feature importance weighting, modeling of spatial relationships, and adaptive learning capabilities, the model BETAM pays more attention to edge features, thus improving the accuracy of edge detection. A remote sensing image dataset SMCD (Subject Meticulous Categorization Dataset) is constructed to verify the robustness of the attention mechanism BETAM and the model DeepBETAM. Extensive experiments were conducted on the two self-built datasets FRSID and SMCD. Experimental results showed that the mean Intersection over Union (mIoU), mean Pixel Accuracy (mPA), and mean Recall (mRecall) of DeepBETAM are 63.64%, 71.27%, and 71.31%, respectively. These metrics are superior to DeeplabV3+, DeeplabV3+(SENet), DeeplabV3+(CBAM), DeeplabV3+(SAM), DeeplabV3+(ECANet), and DeeplabV3+(CAM), which are network models that incorporate different attention mechanisms. The reason is that BETAM has better edge segmentation results and segmentation accuracy. Meanwhile, on the basis of the self-built dataset, the four main classifications of buildings, cultivated land, water bodies and vegetation were subdivided and detected, and good experimental results were obtained, which verified the robustness of the attention mechanism BETAM and the model DeepBETAM. The method has broad application prospects and can provide favorable support for research and application in the field of surface classification. [ABSTRACT FROM AUTHOR]

Symmetries and symmetry-breaking play significant roles in data security. While remote sensing images, being extremely sensitive geospatial data, require protection against tampering or destruction, as well as assurance of the reliability of the data source during application. In view of the increasing complexity of data security of remote sensing images, a single watermark algorithm is no longer adequate to meet the demand of sophisticated applications. Therefore, this study proposes a dual watermarking algorithm that considers both integrity authentication and copyright protection of remote sensing images. The algorithm utilizes Discrete Wavelet Transform (DWT) to decompose remote sensing images, then constructs integrity watermark information by applying Chebyshev mapping to the mean of horizontal and vertical components. This semi-fragile watermark information is embedded into the high-frequency region of DWT using Quantization Index Modulation (QIM). On the other hand, the robust watermarking uses entropy to determine the embedding position within the DWT domain. It combines the stability of Singular Value Decomposition (SVD) and embeds the watermark according to the relationship between the singular values of horizontal, vertical, and high-frequency components. The experiment showed that the proposed watermarking successfully maintains a high level of invisibility even if embedded with dual watermarks. The semi-fragile watermark can accurately identify tampered regions in remote sensing images under conventional image processing. Moreover, the robust watermark exhibits excellent resistance to various attacks such as noise, filtering, compression, panning, rotating, and scaling. [ABSTRACT FROM AUTHOR]

Fast and accurate detection of ship objects in remote sensing images must overcome two critical problems: the complex content of remote sensing images and the large number of small objects reduce ship detection efficiency. In addition, most existing deep learning-based object detection models require vast amounts of computation for training and prediction, making them difficult to deploy on mobile devices. This paper focuses on an efficient and lightweight ship detection model. A new efficient ship detection model based on device–cloud collaboration is proposed, which achieves joint optimization by fusing the semantic segmentation module and the object detection module. We migrate model training, image storage, and semantic segmentation, which require a lot of computational power, to the cloud. For the front end, we design a mask-based detection module that ignores the computation of nonwater regions and reduces the generation and postprocessing time of candidate bounding boxes. In addition, the coordinate attention module and confluence algorithm are introduced to better adapt to the environment with dense small objects and substantial occlusion. Experimental results show that our device–cloud collaborative approach reduces the computational effort while improving the detection speed by 42.6% and also outperforms other methods in terms of detection accuracy and number of parameters. [ABSTRACT FROM AUTHOR]

Remote sensing images acquired under bad weather conditions often suffer from serious degradation such as color distortion, blur and low contrast, which seriously affects their application in vision tasks. To this end, a two-stage fusion dehazing network, termed TSFDNet, is proposed to remove the haze in remote sensing images effectively. In the first stage, the preliminary dehazing sub-network is designed to remove haze, which employs a multi-scale feature extraction block to aware haze density features to enhance the dehazing effect. In the second stage, the refined dehazing and detail compensation sub-network is designed to refine dehazing and compensate for image details by utilizing edge information and pixel-channel hybrid attention residual modules. Finally, the potentially beneficial features of the two stages are fused to improve the model performance. Experiments on multiple datasets have shown that the proposed model performs better in quantitative and qualitative evaluations than the compared methods. Furthermore, the effectiveness of key components of the model has been verified by ablation studies. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the development of computer vision and remote sensor devices, object detection in aerial images has drawn considerable attention because of its ability to provide a wide field of view and a large amount of information. Despite this, object detection in aerial images is a challenging task owing to densely packed objects, oriented diversity, and complex background. In this study, we optimized three aspects of the YOLOv5 algorithm to detect arbitrary oriented objects in remote sensing images, including head structure, features from the backbone, and angle prediction. To improve the head structure, we decoupled it into four submodules, which are used for object localization, foreground, category, and oriented angle classification. To increase the accuracy of the features from the backbone, we designed a block dimensional attention module, which is developed by splitting the image into smaller patches based on a dimensional attention module. Compared with the original YOLOv5 algorithm, our approach has a better performance for oriented object detection-the mAP on DOTA-v1.5 is increased by 1.25%. It was tested to be effective on DOTA-vl.0, HRSC2016, and DIOR-R datasets as well. [ABSTRACT FROM AUTHOR]

With the advancement in satellite and Artificial Intelligence (AI), the increase in observation of the earth is increasing dramatically. With this development, the demand in the field of Remote Sensing (RS) is also growing rapidly. The spatial resolution and textural information of remote sensing images can be improved by introducing AI and Machine Learning (ML) technology. In the modern era of computer science, Deep Learning (DL) models are more familiar in the field of scene classification. This paper aims to develop a novel depth-wise CNN model to classify the RS images with low time effort during training with higher accuracy than the existing CNN model. For comparison, three typical CNN models of VGG16, VGG19, ResNet50 and RegNet are taken and tested on the RS datasets for classification. The experimented analysis demonstrates that the proposed classification model surpasses the existing classification models by producing higher accuracy in testing by taking a minimum time duration for training the RS datasets. [ABSTRACT FROM AUTHOR]

The proliferation of remote sensing image data in recent years has posed a pressing need for efficient compression techniques due to constrained transmission bandwidth. While lossless compression preserves image fidelity, it falls short of meeting real-time demands. Conversely, conventional lossy compression methods can attain high compression ratios for real-time applications, but often introduce issues like block artifacts, blurring, and distortions in the decompressed images. Hence, we propose the Global Feature-Assisted Segmentation Compression Network (GFSCompNet) as a solution for high compression ratio lossy compression. Initially, we design a segmentation network utilizing a dual-branch global feature-assisted segmentation approach to precisely detect small targets in remote sensing images. On the compression side of the network, we leverage an attention mechanism and code rate allocation technique to seamlessly merge the segmented small target information with the original image, thereby allocating a higher compression code rate to the small target region. Furthermore, a joint hyper-priority decoding and entropy coding estimation network is proposed to further remove the redundancy in the potential representation and improve the compression ratio. Experimental results conducted under conditions of high compression ratios and comparable bit rates demonstrate that our approach yields higher-quality reconstructed images compared to the JPEG algorithm and outperforms other deep learning-based image compression methods. Additionally, it effectively preserves small target information, thereby enhancing the interpretability of machine learning models. [ABSTRACT FROM AUTHOR]

Change detection (CD) in high-resolution remote sensing imagery remains challenging due to the complex nature of objects and varying spectral characteristics across different times and locations. Convolutional neural networks (CNNs) have shown promising performance in CD tasks by extracting meaningful semantic features. However, traditional 2D-CNNs may struggle to accurately integrate deep features from multi-temporal images, limiting their ability to improve CD accuracy. This study proposes a Multi-level Feature Cross-Fusion (MFCF) network with 3D-CNNs for remote sensing image change detection. The network aims to effectively extract and fuse deep features from multi-temporal images to identify surface changes. To bridge the semantic gap between high-level and low-level features, a MFCF module is introduced. A channel attention mechanism (CAM) is also integrated to enhance model performance, interpretability, and generalization capabilities. The proposed methodology is validated on the LEVIR construction dataset (LEVIR-CD). The experimental results demonstrate superior performance compared to the current state-of-the-art in evaluation metrics including recall, F1 score, and IOU. The MFCF network, which combines 3D-CNNs and a CAM, effectively utilizes multi-temporal information and deep feature fusion, resulting in precise and reliable change detection in remote sensing imagery. This study significantly contributes to the advancement of change detection methods, facilitating more efficient management and decision making across various domains such as urban planning, natural resource management, and environmental monitoring. [ABSTRACT FROM AUTHOR]

Weakly supervised learning plays a pivotal role in the field of object detection, i.e. Weakly supervised object detection (WSOD), significantly reducing annotation costs relying on image-level labels. However, WSOD exhibits certain limitations. Typically, they tend to identify the most easily recognizable local regions within targets, posing challenges in accurately delineating the boundaries of targets. Moreover, the presence of multiple instances of the same class in adjacent locations complicates the effective distinction between multiple objects within the same category. On the other hand, the complex backgrounds and dense distribution of targets in remote sensing images (RSI) further exacerbate the difficulty of weakly supervised detection. To address the above issues, we propose a model termed the Multi-View Contextual Adaptation Network (VCANet). Building on the classic Online Instance Classifier Refinement (OICR) framework, we propose to incorporate an contextual adaptation perception, within a multi-view learning framework, and integrate a pseudo-label filtering process. The contextual adaptation perception utilizes the surrounding environment information to enhance localization capabilities, guiding the model to prioritize target objects by referring to their spatially neighbouring pixels. Multi-view learning manufactures additional constraints from diverse perspectives, thereby revealing objects that might be overlooked due to the weak supervision in a single view. The pseudo-label filtering process eliminates inaccurate pseudo-labels by identifying reliable foregrounds to mitigate overlapping proposals during the label propagation. On challenging datasets NWPU VHR-10.v2 and DIOR, we achieve promising results with mAP of 62.3% and 28.2%, respectively, surpassing existing benchmarks. [ABSTRACT FROM AUTHOR]

Segmenting clouds and their shadows is a critical challenge in remote sensing image processing. The shape, texture, lighting conditions, and background of clouds and their shadows impact the effectiveness of cloud detection. Currently, architectures that maintain high resolution throughout the entire information-extraction process are rapidly emerging. This parallel architecture, combining high and low resolutions, produces detailed high-resolution representations, enhancing segmentation prediction accuracy. This paper continues the parallel architecture of high and low resolution. When handling high- and low-resolution images, this paper employs a hybrid approach combining the Transformer and CNN models. This method facilitates interaction between the two models, enabling the extraction of both semantic and spatial details from the images. To address the challenge of inadequate fusion and significant information loss between high- and low-resolution images, this paper introduces a method based on ASMA (Axial Sharing Mixed Attention). This approach establishes pixel-level dependencies between high-resolution and low-resolution images, aiming to enhance the efficiency of image fusion. In addition, to enhance the effective focus on critical information in remote sensing images, the AGM (Attention Guide Module) is introduced, to integrate attention elements from original features into ASMA, to alleviate the problem of insufficient channel modeling of the self-attention mechanism. Our experimental results on the Cloud and Cloud Shadow dataset, the SPARCS dataset, and the CSWV dataset demonstrate the effectiveness of our method, surpassing the state-of-the-art techniques for cloud and cloud shadow segmentation. [ABSTRACT FROM AUTHOR]

Image–text multimodal deep semantic segmentation leverages the fusion and alignment of image and text information and provides more prior knowledge for segmentation tasks. It is worth exploring image–text multimodal semantic segmentation for remote sensing images. In this paper, we propose a bidirectional feature fusion and enhanced alignment-based multimodal semantic segmentation model (BEMSeg) for remote sensing images. Specifically, BEMSeg first extracts image and text features by image and text encoders, respectively, and then the features are provided for fusion and alignment to obtain complementary multimodal feature representation. Secondly, a bidirectional feature fusion module is proposed, which employs self-attention and cross-attention to adaptively fuse image and text features of different modalities, thus reducing the differences between multimodal features. For multimodal feature alignment, the similarity between the image pixel features and text features is computed to obtain a pixel–text score map. Thirdly, we propose a category-based pixel-level contrastive learning on the score map to reduce the differences among the same category's pixels and increase the differences among the different categories' pixels, thereby enhancing the alignment effect. Additionally, a positive and negative sample selection strategy based on different images is explored during contrastive learning. Averaging pixel values across different training images for each category to set positive and negative samples compares global pixel information while also limiting sample quantity and reducing computational costs. Finally, the fused image features and aligned pixel–text score map are concatenated and fed into the decoder to predict the segmentation results. Experimental results on the ISPRS Potsdam, Vaihingen, and LoveDA datasets demonstrate that BEMSeg is superior to comparison methods on the Potsdam and Vaihingen datasets, with improvements in mIoU ranging from 0.57% to 5.59% and 0.48% to 6.15%, and compared with Transformer-based methods, BEMSeg also performs competitively on LoveDA dataset with improvements in mIoU ranging from 0.37% to 7.14%. [ABSTRACT FROM AUTHOR]

Remote sensing image object detection is widely used in civil and military fields. The important task is to detect objects such as ships, planes, airports, harbours and so on, and then it can obtain object category and position information. It is of great significance to use remote sensing images to observe the densely arranged and directional targets such as cars and ships parked in parking lots and harbours. The object detection task mainly includes object localization and classification. Remote sensing images contain large number of small objects and dense scenes due to the long shooting distance and wide coverage. Small objects occupy few pixels in the image, and they are easily miss‐detected. In dense scenes, the overlapping part of each object is large, so it is easy to detect objects repeatedly. The traditional small object detection methods deliver low accuracy and take long time. Therefore, object detection is very challenging. We put forward a novel deep learning‐based single shot multibox detector (SSD) model for object detection. First, we propose an improved inception network to optimize SSD to strengthen the small object feature extraction ability (FEA) in the shallow network. Second, the feature pyramid network is modified to enhance the fusion effect. Third, the deep feature fusion module is designed to improve the FEA of the deep network. Finally, the extracted image features are matched with candidate boxes with different aspect ratios to perform object detection and location with different scales. Experiments on DOTA show that the proposed algorithm can adapt to the remote sensing object detection in different backgrounds, and effectively improve the detection effect of remote sensing objects in complex scenes. [ABSTRACT FROM AUTHOR]

Credit evaluation has always been an important part of the financial field. The existing credit evaluation methods have difficulty in solving the problems of redundant data features and imbalanced samples. In response to the above issues, an ensemble model combining an advanced feature selection algorithm and an optimized loss function is proposed, which can be applied in the field of credit evaluation and improve the risk management ability of financial institutions. Firstly, the Boruta algorithm is embedded for feature selection, which can effectively reduce the data dimension and noise and improve the model's capacity for generalization by automatically identifying and screening out features that are highly correlated with target variables. Then, the GHM loss function is incorporated into the XGBoost model to tackle the issue of skewed sample distribution, which is common in classification, and further improve the classification and prediction performance of the model. The comparative experiments on four large datasets demonstrate that the proposed method is superior to the existing mainstream methods and can effectively extract features and handle the problem of imbalanced samples. [ABSTRACT FROM AUTHOR]

Copyright of Journal of South-Central Minzu University (Natural Science Edition) is the property of Journal of South-Central Minzu University (Natural Science Edition) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)