检索结果-内蒙古大学图书馆

Self-supervised polarization image dehazing method via frequency domain generative adversarial networks

pattern recognition 2025年 165卷

作者： Sun, Rui Chen, Long Liao, Tanbin Fan, Zhiguo Hefei Univ Technol Sch Comp Sci & Informat Engn 485 Danxia Rd Hefei 230009 Peoples R China Hefei Univ Technol Key Lab Ind Safety & Emergency Technol Hefei 230009 Peoples R China Minist Educ Peoples Republ China Key Lab Knowledge Engn Big Data Hefei 230009 Peoples R China

Haze significantly hinders the application of autonomous driving, traffic surveillance, and remote sensing. image dehazing serves as a key technology to enhance the clarity of images captured in hazy conditions. However, the lack of paired annotated training data significantly limits the performance of deep learning-based dehazing methods in real-world scenarios. In this work, we propose a self-supervised polarization image dehazing framework based on frequency domain generative adversarial networks. By incorporating a polarization calculation module into the generator, the Stokes parameters of airlight are accurately estimated, which are used to reconstruct the synthesized hazy image by combining the dehazed image generated via a densely connected encoder-decoder. Furthermore, we optimize the discriminator with frequency domain features extracted by frequency decomposition module and introduce a pseudo airlight coefficient supervision loss to enhance the selfsupervised training. By discriminating between synthetic hazy images and real hazy images, we achieve adversarial training without the need for paired data. Simultaneously, supervised by the atmospheric scattering model, our network can iteratively generate more realistic dehazed images. Extensive experiments conducted on the constructed multi-view polarization datasets demonstrate that our method achieves state-of-the-art performance without requiring real-world ground truth.

关键词： image dehazing Polarization image Frequency domain Self-supervised Generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Effective delineation of rare metal-bearing granites from remote sensing data using machine learning methods: A case study from the Umm Naggat Area, Central Eastern Desert, Egypt

引用

ORE GEOLOGY REVIEWS 2022年 150卷

作者： Abdelkader, Mohamed A. Watanabe, Yasushi Shebl, Ali El-Dokouny, Hanna A. Dawoud, Maher Csamer, Arpad Akita Univ Dept Earth Resource Sci Akita Japan Menoufia Univ Fac Sci Dept Geol Shibin Al Kawm Egypt Univ Debrecen Dept Mineral & Geol Debrecen Hungary Tanta Univ Fac Sci Dept Geol Tanta Egypt

Albitized granite (ABG) is considered as one of the most significant hosts of rare metals (RMs). Consequently, adequate recognition of ABG through proper lithological discrimination highly increases the targeting of rare metal resources. In order to delineate outcrops of ABG from satellite data, our study integrates eight image enhancement techniques, including optimum index factor, false color composites, band rationing, relative band depth, independent component analysis, principal component analysis, decorrelation stretch, minimum noise fraction transform, and spectral indices ratios, for the interpretation of ASTER and Sentinel-2 (S2) datasets. This integrated approach allows the effective discrimination of AGB outcrops in the Umm Naggat area, Central Eastern Desert, Egypt. The interpretation maps derived from these integrated image processing techniques were systematically verified in the field and formed the base for the feature selection process (i.e., training and testing data delineation) of different lithologies supported by the support vector machine algorithm (SVM). In order produce a high-quality lithological interpretation map, SVM was applied to Sentinel-2, ASTER, and combined ASTER-S2 datasets. The fused ASTER-S2 classification properly delineates ABG, as verified by our field vestigations and confirmed by previous geological maps. Furthermore, comprehensive structural analysis (lin-eaments extraction and their density map) and hydrothermal alteration detection were performed to check the spatial association between the distribution of ABG, higher density zones, and highly altered areas, that in turn, could shed light on new potentially mineralized zones and proposed exploration targets. Our study reveals new ABG occurrences mainly situated in the southern and southwestern parts of the study area, and it confirms the location of known mineralized zones in the northern part of the Umm Naggat region. The distribution of ABG and its spatial correlation

关键词： Sentinel-2 ASTER Support Vector Machine Albitized granite Integrated image processing techniques Rare-metal exploration Central Eastern Desert Egypt

来源：评论

学校读者我要写书评

暂无评论

A COMBINED APPROACH FOR LONG-TERM MONITORING OF BENTHOS IN ANTARCTICA WITH UNDERWATER PHOTOGRAMMETRY AND image UNDERSTANDING 24

A COMBINED APPROACH FOR LONG-TERM MONITORING OF BENTHOS IN A...

引用

24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow

作者： Menna, F. Nocerino, E. Malek, S. Remondino, F. Schiaparelli, S. Bruno Kessler Fdn FBK 3D Opt Metrol 3DOM Unit Trento Italy Univ Sassari Dipartimento Sci Umanist & Sociali Sassari Italy Univ Genoa DISTAV Genoa Italy Italian Natl Antarctic Museum MNA Sect Genoa Genoa Italy

Long-term monitoring projects are becoming more than ever crucial in assessing the effects of climate change on marine communities, especially in Antarctica, where these changes are expected to be particularly dramatic. Detailed studies of the Antarctic benthos are in fact particularly important for a better understanding of benthos dynamics and potential climate-driven shifts. Here, due to the extreme fragility of benthic communities, non-destructive techniques represent the best solution in long-term monitoring programs. In this paper we report new results from 2017, 2018, 2019 photogrammetric campaigns within the Italian National Antarctic Research Program (PNRA). A new protocol of data acquisition and multi-temporal processing that provides co-registered 3D point clouds between the three years without control points nor direct georeferencing methods is presented. This is achieved by adding a level of image understanding leveraging semantic segmentation with convolutional neural network (CNN) of the benthic features. Slow growing (estimated less than a mm per year) organisms, such as Corallinales (Rhodophyta algae), represent a natural stable pattern, leveraged to automatically orient in the same reference system the photogrammetric surveys of different epochs. This approach is also proved to be effective in improving the orientation of adjacent strips acquired within the same campaign. Within the paper an in depth analysis of the achieved results shows the effectiveness of the implemented procedure.

关键词： Underwater photogrammetry change detection long-term monitoring antarctica image segmentation CNN

来源：评论

学校读者我要写书评

暂无评论

VQARS: Visual Question Answering for remote sensing as a Domain of Choice Incorporating Semantic Intelligence 15th

VQARS: Visual Question Answering for Remote Sensing as a Dom...

引用

15th International Conference on Soft Computing and pattern recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Manoj Kumar, H.S. Deepak, Gerard Santhanavijayan, A. Department of Computer Science and Engineering PES University Bangalore India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli Tiruchirappalli India

ISBN: (纸本)9783031889912

The need for a visual question answering framework in the era of Web 3.0 is realized by using staged addition of auxiliary knowledge in the perspective of two distinct datasets namely the dataset of documents and the images which is enriched through informative term extraction and further using structural topic modelling, Wikidata, NELL and Linked Open Data (LOD) Cloud, knowledge stores and tag generation to classify the dataset obtained informative terms. Subsequently, the image dataset terms are subjected to extraction of categories and labels to contribute to the informative terms. The random forest classifier at either ends of the two datasets helps in controlled classification of the datasets independently and assures computational inexpensiveness because of the lightweighted nature of the machine learning classifiers. The RNN to classify the tags helps in automatizing the exponentially generated tags and semantic network formulated helps in organizing the auxiliary knowledge. Semantic relevance computation using Jaccard Similarity, Morisitas Overlap Index, NPMI and SOC-PMI facilitates in semantic reasoning. The proposed VQARS model's achieves an overall precision of 94.81%;recall of 95.75%;average accuracy of 95.28%;F-measure of 95.28%;and the lowest FDR of 0.06. In comparison to the other baseline models, this model provides the best-in-class outcomes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Information supplement based on Tip-adapter

Information supplement based on Tip-adapter

引用

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Shengzhou Lian Xu Tang School of Artificial Intelligence Xidian University Xian China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The Contrast Language-image Pre-training (CLIP) model learns to associate image and text content by pre-training on a large number of image and text pairs. The CLIP model can understand the relationship between image content and text description, thereby achieving functions such as image recognition, classification, and retrieval in various tasks. And due to its zero sample learning ability, it can perform effective task inference even without a large amount of labeled data. The proposal of CLIP model has brought new research ideas and application possibilities to the field of multimodal learning, and has shown excellent performance in the zero-shot domain. When we want to apply CLIP to the field of few-shot remote sensing image classification, the main challenge is how to fine-tune the knowledge stored in the clip so that the entire model can better adapt to downstream tasks and how to solve the problem of overfitting in training models under the situation of few shot samples. The commonly used CLIP-based fine-tuning methods have poor performance under few-shot conditions. In this paper, we propose a semi-supervised learning based cached model method, which classifies the test set for the first time based on a small amount of labeled data in the training set as the cached model. The high confidence pseudo labeled data in the test set is used as a supplement to jointly classify the remaining low confidence test samples. The experiment shows that our proposed innovative method has significantly improved accuracy compared to previous methods on two benchmark datasets.

关键词： Training Adaptation models image recognition Semisupervised learning Data models Sensors Proposals remote sensing Overfitting image classification

来源：评论

学校读者我要写书评

暂无评论

Material Inspection of Historical Built Heritage with Multi-Band images: A Case Study of the Serranos Towers in Valencia

引用

remote sensing 2024年第17期16卷 3167页

作者： Alicandro, Maria Mileto, Camilla Lerma, Jose Luis Univ Aquila Dept Civil Construct Architectural & Environm Engn Via Gronchi 18 I-67100 Laquila Italy Univ Politecn Valencia Dept Architectural Composit Camino Vera S-N Valencia 46022 Spain Univ Politecn Valencia Dept Cartog Engn Geodesy & Photogrammetry Camino Vera S-N Valencia 46022 Spain

Built heritage materials assessment is an important task for planning and managing future conservation works. The uniqueness of each historical building makes reconnaissance operations more complex and specific for every single building. In the past, visual inspection and invasive techniques were widely used to investigate surface materials. Non-destructive techniques (NDTs) such as multi-band photogrammetry and remote sensing can help to assess the buildings without any contact with the investigated objects, restricting the disruptive tests on limited areas and reducing the testing time and costs of the surveys. This paper presents the results obtained using multi-band images acquired with a low-cost imaging solution after interchanging several filters, and the application of the principal components analysis (PCA) to recognize different materials of a significant historical monument. The Serranos Towers, built between 1392 and 1398, suffered several interventions in the past that affected their state of conservation with the replacement of different materials. The results of the study show the usefulness of applying PCA to distinguish different surface materials, often similar to the original ones, in a fast and efficient way to investigate and analyze our heritage legacy.

关键词： multi-band sensors image processing material recognition PCA medieval tower gate material mapping

来源：评论

学校读者我要写书评

暂无评论

Accurate Angle Detection of Rotated Rectangles Using Hybrid Architecture of Convolutional Neural Networks with Multi-Layer Perceptron and SVR

Accurate Angle Detection of Rotated Rectangles Using Hybrid ...

引用

International Conference on Emerging Trends in Networks and Computer Communications (ETNCC)

作者： Nayeem Ahmed Faculty of Electrical and Computer Engineering Technische Universität Dresden Dresden Germany

ISBN: (数字)9798350353266

ISBN: (纸本)9798350353273

This study presents a novel approach for detecting the angles of the rotated rectangles precisely using the hybrid architecture of Convolutional Neural Networks (CNN) with Multi-Layer Perceptron (MLP) and Support Vector Regression (SVR). This work also shows the comparative assessment between the two hybrid models, CNN & MLP only and CNN & MLP along with the SVR for unrolling the angles of the rectangles. In the automated image analysis and pattern recognition domain, the complexity of rotated rectangles-especially in different orientations and scales-presents formidable challenges. Our study begins with the dataset comprised of 10000 images of rectangles with varying rotation angles and coordinates. Then, CNN, an effective model in the image analysis and computer vision field, effectively captures the spatial dependencies and characteristics of rotated rectangles from the raw images by extracting and learning the hierarchical feature representations. To further process the pieces of information, the MLP and SVR are used, giving the learning model more depth and improving its capacity to recognize complex patterns. Evaluation metrics such as MSE, RMSE, MAPE, MAE, and $\mathbf{R}^pattern$ determine the model's accuracy. This research enhances the fields of machine learning and image processing and also potentially benefits robotics, com-puter vision, and remote sensing-all of which depend on precise geometric interpretation. The evaluation metrics corroborate that the algorithm based on CNN and MLP along with the SVR has better accuracy compared to the model that relies only on CNN and MLP.

关键词： Measurement Analytical models image analysis Accuracy Computational modeling Computer architecture Feature extraction Data models pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Target detection of remote sensing images based on deep learning method and system 3

Target detection of remote sensing images based on deep lear...

引用

3rd International Conference on Advanced Information Science and System, AISS 2021

作者： Wang, Su Jun Ping, Yi Fan Chen, Gang Yang, Li Wen, Wei Xu, Chang Zhi Shao, Ying Zhao China Academy of Space Technology China

ISBN: (纸本)9781450385862

With the rapid growth of remote sensing image data, it is very important to find a way to extract and recognize the target quickly and accurately from the massive remote sensing data. In recent years, the development of deep learning has provided an effective way for target detection of remote sensing images. This paper applies deep learning technology to target detection of remote sensing images, and constructs a target detection system software which integrates sample labeling, data set construction, pretreatment of training sample, training algorithm, migration learning, target recognition and post processing. It provides technical support to the tasks of classification, information extraction and change detection of remote sensing image. The experimental results show that the target recognition system of remote sensing images has high precision in the scene classification and specific target detection of high-resolution remote sensing images. © 2021 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Balancing Data Imbalance in remote sensing image Road Segmentation with Gradient-Guided Multi-level Data Augmentation

引用

IEEE Signal processing Letters 2025年 32卷 2404-2408页

作者： Cao, Xu Liu, Weisheng Wang, Zhijian University of Science and Technology Liaoning College of Computer Science and Software Engineering Anshan China

In remote sensing image segmentation, data imbalance remains a critical challenge, particularly in datasets from networks and natural scenes, increasing task complexity. Recent studies have explored adversarial training to address this issue, but these methods rely heavily on labeled data, introducing annotation bias and efficiency concerns. To overcome these limitations, this paper proposes a gradient-guided image-level perturbation strategy. Specifically, we design a multi-level, multi angle data augmentation framework that integrates patch-level perturbation with gradient-based adaptive region selection, enhancing the model's recognition of rare samples while preserving contextual integrity. Experimental results demonstrate that our method surpasses traditional segmentation algorithms and data balancing strategies, achieving an F1 score of 82.67% on the Massachusetts Roads dataset and exhibiting strong generalization on the LoveDA dataset. This research provides valuable insights for advancing remote sensing image analysis. © 1994-2012 IEEE.

关键词： Data Imbalance Gradient Guidance Multi-level Data Augmentation remote sensing image Segmentation Road Segmentation

来源：评论

学校读者我要写书评

暂无评论

remote sensing image Captioning Using Hire-MLP

Remote Sensing Image Captioning Using Hire-MLP

引用

Computer Vision, image and Deep Learning (CVIDL), International Conference on

作者： Yichao Wei Lin Li Shengling Geng School of Computer Science Qinghai Normal University Xining China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining China Academy of Plateau Science and Sustainability Qinghai Normal University Xining China National Qinghai-Tibet Plateau Scientific Data Center Qinghai Sub-center Xining China

remote sensing image captioning has been widely applied to traffic management, geographic research, etc. Although the neural network approach has been successfully improving the performance of the remote sensing image captioning system, remote sensing image captioning is still facing object identification challenges due to the small size of objects, uneven distribution, and high coupling with the surrounding image background. In this paper, we propose a novel remote sensing image captioning encoder-decoder model Hierarchical rearrangement-Multi-Layer Perceptron (HMLP) whose encoder adapts hierarchical rearrangement-multi-layer perceptron to improve the capability of objection recognition. Extensive experiments have been conducted to testify HMLP by three datasets RSCID, UCM-caption, and NWPU-caption. Results show that HMLP outperforms many image captioning systems in the evaluation metrics BLEU4, METEOR, ROUGE-L, and CIDEr.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：