IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society最新文献_第10页

Module-Pruning-Based Neural Architectural Search for Remote Sensing Image Captioning 基于模块剪枝的遥感图像标题神经结构搜索

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-08-04 DOI: 10.1109/LGRS.2025.3593475

Yogendra Rao Musunuri;Changwon Kim;Oh-Seol Kwon;Sun-Yuan Kung

{"title":"Module-Pruning-Based Neural Architectural Search for Remote Sensing Image Captioning","authors":"Yogendra Rao Musunuri;Changwon Kim;Oh-Seol Kwon;Sun-Yuan Kung","doi":"10.1109/LGRS.2025.3593475","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3593475","url":null,"abstract":"Remote sensing image captioning (RSIC) has garnered significant attention for enhancing the interpretability of aerial imagery through textual descriptions. Conventional approaches employ convolutional neural networks (CNNs) for visual feature extraction paired with recurrent neural networks (RNNs) or transformers for caption generation. However, these architectures suffer from high complexity and computational costs. While neural architecture search (NAS) via network pruning has been extensively studied, module-based pruning for RSIC systems remains largely unexplored. We propose a novel dedicated decoder pruning methodology for sequential caption generators—a module-based pruning method for end-to-end encoder–decoder architectural adaptation. It features two key innovations: 1) structured pruning of a pre-trained ResNet encoder and transformer encoder–decoder components and 2) a cross-entropy-based caption matching strategy replacing conventional prediction training in the decoder’s final layer. The proposed method enables simultaneously enhancing inference efficiency and reducing storage requirements without compromising performance. As evaluated on the RSICD dataset using CIDEr, ROUGE, METEOR, bilingual evaluation understudy (BLEU), and Sm metrics, our method achieves 42.8% model size reduction while improving accuracy, establishing new benchmarks in efficient RSIC.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2025-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Normalized Radar Burn Ratio: A Case Study for Burned Area Mapping in Mediterranean Forests 归一化雷达烧蚀比：地中海森林烧蚀面积测绘的案例研究

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-25 DOI: 10.1109/LGRS.2025.3592093

Yonatan Tarazona;M. A. Tanase;Vasco Mantas

引用次数: 0

Multiple Object Tracking in Video SAR: A Benchmark and Tracking Baseline 视频SAR中的多目标跟踪：基准和跟踪基线

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-25 DOI: 10.1109/LGRS.2025.3592711

Haoxiang Chen;Wei Zhao;Rufei Zhang;Nannan Li;Dongjin Li

{"title":"Multiple Object Tracking in Video SAR: A Benchmark and Tracking Baseline","authors":"Haoxiang Chen;Wei Zhao;Rufei Zhang;Nannan Li;Dongjin Li","doi":"10.1109/LGRS.2025.3592711","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3592711","url":null,"abstract":"In the context of multiobject tracking using video synthetic aperture radar (Video SAR), Doppler shifts induced by target motion result in artifacts that are easily mistaken for shadows caused by static occlusions. Moreover, appearance changes of the target caused by Doppler mismatch may lead to association failures and disrupt trajectory continuity. A major limitation in this field is the lack of public benchmark datasets for standardized algorithm evaluation. To address the above challenges, we collected and annotated 45 video SAR sequences containing moving targets, and named the video SAR MOT benchmark (VSMB). Specifically, to mitigate the effects of trailing and defocusing in moving targets, we introduce a line feature enhancement mechanism that emphasizes the positive role of motion shadows and reduces false alarms induced by static occlusions. In addition, to mitigate the adverse effects of target appearance variations, we propose a motion-aware clue discarding mechanism that substantially improves tracking robustness in video SAR. The proposed model achieves state-of-the-art performance on the VSMB, and the dataset and model are released at <uri>https://github.com/softwarePupil/VSMB</uri>","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bloch Sphere Representation of Polarimetric SAR Targets 极化SAR目标的Bloch球表示

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-24 DOI: 10.1109/LGRS.2025.3592360

Avik Bhattacharya;Abhinav Verma

引用次数: 0

Enhanced RSVQA Insight Through Synergistic Visual-Linguistic Attention Models 通过协同视觉语言注意模型增强RSVQA洞察

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-24 DOI: 10.1109/LGRS.2025.3592253

Anirban Saha;Suman Kumar Maji

{"title":"Enhanced RSVQA Insight Through Synergistic Visual-Linguistic Attention Models","authors":"Anirban Saha;Suman Kumar Maji","doi":"10.1109/LGRS.2025.3592253","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3592253","url":null,"abstract":"The interpretation of remote sensing images remains a significant challenge due to their complex, information-rich nature. Current remote sensing visual question answering (RSVQA) techniques have been a step forward toward building intelligent analysis systems for remote sensing images. However, most existing RSVQA models that rely on ResNet, VGG, and Swin transformers as visual feature extractors often fail to capture complex visual relationships, particularly the intricate dependencies between segmented regions and depth-related features in remote sensing data. To address these limitations, this letter introduces a novel RSVQA approach that leverages state-of-the-art components with an innovative architecture to advance interactive remote sensing analysis. The proposed model features a novel dual-layer visual attention mechanism in the representation module to process intricate features and capture regional relationships alongside processing the overall features. The fusion module employs a unique attention-based design, combining both self-attention and mutual attention, to integrate these features into a unified vector representation. Finally, the answering module utilizes a refined multilayer perceptron classifier for precise response generation. Evaluations on an RSVQA benchmark demonstrate the system’s superiority over existing methods, marking a significant step forward in remote sensing analytics.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Application of Point Spread Function in Tunnel Seismic Prediction 点扩展函数在隧道地震预报中的应用

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-24 DOI: 10.1109/LGRS.2025.3592307

Zhimin Yan;Jingrui Luo;Huamin Zhou;Xingguo Huang

{"title":"Application of Point Spread Function in Tunnel Seismic Prediction","authors":"Zhimin Yan;Jingrui Luo;Huamin Zhou;Xingguo Huang","doi":"10.1109/LGRS.2025.3592307","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3592307","url":null,"abstract":"Tunnel seismic prediction (TSP) is essential for guaranteeing the safety of tunnel construction. Reverse time migration (RTM) plays a vital role in providing precise visualization of the geology located in front of the tunnel. However, anomalies like karst caves cause signal reflection and attenuation, leading to blurred images and artifacts. The point spread function (PSF) characterizes the blurring effect of a specific observing system on an imaging point, and the migration result can be viewed as the convolution of the true reflectance model with the PSF. Thus, the ambiguity of the migration result can be eliminated by using the inverse of the PSF. In this letter, we utilize the PSF in the context of TSP. First, the wavefields from the source and receiver sides are broken down into angle domain components through the Poynting vector approach. Then, the PSF operator is obtained by calculating the local illumination matrix (LIM) and is further applied to image correction. We designed various models to simulate the complex geology in front of the tunnel. Numerical experiments show that the application of PSF can improve the imaging accuracy of complex structures in TSP. The test results of actual tunnel seismic data also demonstrate the effectiveness of this method.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D-HRSCD: Exploiting the Potential of Multiscale Features by 3-D Convolution 3D-HRSCD：利用三维卷积挖掘多尺度特征的潜力

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-22 DOI: 10.1109/LGRS.2025.3591276

Yue Song;Sheng Fang;Zhe Li;Su Wang;Enyi Zhao

{"title":"3D-HRSCD: Exploiting the Potential of Multiscale Features by 3-D Convolution","authors":"Yue Song;Sheng Fang;Zhe Li;Su Wang;Enyi Zhao","doi":"10.1109/LGRS.2025.3591276","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3591276","url":null,"abstract":"Semantic change detection (SCD) in remote sensing image (RSI) is critical for monitoring land cover and land-use transformations. Although existing SCD methods have made progress in modeling temporal dependency, they still struggle to effectively capture multiscale features and make interaction among them. To address these issues, we propose 3D-HRSCD, a novel architecture that utilizes 3-D convolution to model temporal dependency across HRNet’s multiresolution features. The core of this architecture is 3-D convolution fusion oriented to multiscale (3DFOM) features module, which makes adequate interaction in channel, spatial, and temporal dimensions across multiscale features. To support more efficient temporal dependency modeling in 3DFOM, cosine similarity-based temporal multiscales attention (CTMAs) module serves as a preprocessing stage by enhancing features in change regions. Additionally, comprehensive semantic consistency (CSC) loss function is introduced to further suppress pseudo-changes and reduce semantic recognition errors. Experimental results reveal that our method outperforms state-of-the-art (SOTA) performances relative to previous SCD efforts.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing Label Noise Robustness for Hyperspectral Image Classification by Neighborhood Contrastive Learning 邻域对比学习增强高光谱图像分类的标签噪声鲁棒性

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-22 DOI: 10.1109/LGRS.2025.3591450

Yuanzhuo Xu;Tao Peng;Shaowu Wu;Ruiyi Su;Xiaoguang Niu

{"title":"Enhancing Label Noise Robustness for Hyperspectral Image Classification by Neighborhood Contrastive Learning","authors":"Yuanzhuo Xu;Tao Peng;Shaowu Wu;Ruiyi Su;Xiaoguang Niu","doi":"10.1109/LGRS.2025.3591450","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3591450","url":null,"abstract":"Recent advancements in hyperspectral image classification (HIC) rely on high-quality annotations and thus inevitably suffer from noisy labels. To address the negative effects of noisy labels, some methods employ neighborhood samples to select clean samples and demonstrate promising results. However, they typically rely on robust feature extraction and remain limited under high noise ratios. To overcome the limitations, we propose a novel robust sample selection and correction method based on robust contrastive learning and neighborhood feature modeling. The proposed RSC adopts a dual-branch spectral–spatial network combining spatial and channel-based residual attention modules to extract robust feature. Furthermore, unsupervised contrastive learning at both feature and logit level is introduced to bolster the feature extractor. Finally, a clean sample selection strategy based on neighborhood consistency in feature space and relabeling scheme by the maximum confidence are integrated to resist the noisy labels. Extensive experiments conducted on publicly available hyperspectral datasets, including Houston and Indian Pines, demonstrate the superior performance of the proposed method, particularly in high noise ratios, where substantial improvements in classification accuracy are observed. The code is available at <uri>https://github.com/kovelxyz/RSC</uri>","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Quantum-Enhanced Soil Nutrient Estimation Exploiting Hyperspectral Data With Quantum Fourier Transform 利用量子傅立叶变换的高光谱数据进行量子增强土壤养分估算

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-22 DOI: 10.1109/LGRS.2025.3591445

Anand R

{"title":"Quantum-Enhanced Soil Nutrient Estimation Exploiting Hyperspectral Data With Quantum Fourier Transform","authors":"Anand R","doi":"10.1109/LGRS.2025.3591445","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3591445","url":null,"abstract":"Accurate prediction of soil nutrient content is essential for precision agriculture and sustainable land management. Various soil properties, including nitrogen (N), organic carbon (OC), pH, phosphorus (P), and electrical conductivity (EC), exhibit complex oscillatory and quasi-periodic behaviors influenced by environmental cycles, moisture variation, and biological activity. In this study, we propose a novel Fourier quantum convolution (FQC) framework augmented with a quantum entangler circuit to extract robust spectral-domain features from soil spectral data. The proposed FQC entangler circuit processes local spectral patches through parameterized quantum gates and entangling operations, facilitating the extraction of amplitude and phase information while capturing interband correlations. The resulting Fourier quantum features serve as effective inputs to regression models for estimating soil nutrient content. The experimental results demonstrate that the FQC-transformed features significantly enhance the prediction accuracy of N, OC, pH, P, and EC compared to the conventional spectral and statistical features. This study underscores the potential of quantum-inspired feature extraction for advancing digital soil analysis and precision agriculture applications. For instance, on the phosphorus dataset, FQC achieved an RMSE of 3.89 and an <inline-formula> <tex-math>$R^{2}$ </tex-math></inline-formula> of 0.178, outperforming other quantum circuits. Similarly, for the pH dataset, FQC yielded the lowest RMSE (1.16) and MAPE (13.04%), indicating superior generalization and predictive accuracy.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward Effective Knowledge Distillation for Fine-Grained Object Recognition in Remote Sensing 面向遥感细粒度目标识别的有效知识精馏

IF 4.4

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-07-21 DOI: 10.1109/LGRS.2025.3591045

Yangte Gao;Chenwei Deng;Liang Chen

{"title":"Toward Effective Knowledge Distillation for Fine-Grained Object Recognition in Remote Sensing","authors":"Yangte Gao;Chenwei Deng;Liang Chen","doi":"10.1109/LGRS.2025.3591045","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3591045","url":null,"abstract":"With advancements in on-board computing devices deployed on remote sensing platforms, the demand for efficiently processing remote sensing imagery has become increasingly prominent. Knowledge distillation, as an effective lightweight method, has been introduced into this domain. Intuitively, distillation from a larger teacher model is expected to yield better performance. However, in our investigation of fine-grained object recognition in remote sensing imagery, we observed a counter-intuitive phenomenon: as the size of the teacher model increases, the performance of the student model initially improves but then degrades. This capacity gap issue hinders effective utilization of stronger teacher models. To address this issue, we propose a novel distillation framework named BL-KD. It integrates two tailored components: the class-level learnable orthogonal projection (CLOP) module and the object rebalance (ORB) module, which are jointly optimized to mitigate the negative impact of the capacity gap while effectively adapting to the unique distributional patterns and challenges inherent in remote sensing imagery. Experiments conducted on multiple fine-grained object recognition tasks in remote sensing demonstrate that our method consistently improves student performance, particularly in scenarios involving large teacher–student gaps, and outperforms several widely used distillation baselines.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":4.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0