检索结果-内蒙古大学图书馆

IEEE International geoscience and Remote Sensing Symposium

作者： Guowei Chen Lei Liu Wenlong Hu Zongxu Pan Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China

Object detection is a challenging task in computer vision. Now many detection networks can get a good detection result when applying large training dataset. However, annotating sufficient amount of data for training is often time-consuming. To address this problem, a semi-supervised learning based method is proposed in this paper. Semi-supervised learning trains detection networks with few annotated data and massive amount of unannotated data. In the proposed method, Generative Adversarial Network is applied to extract data distribution from unannotated data. The extracted information is then applied to improve the performance of detection network. Experiment shows that the method in this paper greatly improves the detection performance compared with supervised learning using only few annotated data. The results prove that it is possible to achieve acceptable detection result when only few target object is annotated in the training dataset.

关键词： Gallium nitride Generative adversarial networks Detectors Generators Airplanes Training Semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

SUPER-RESOLUTION OF REMOTE SENSING IMAGES BASED ON TRANSFERRED GENERATIVE ADVERSARIAL NETWORK

SUPER-RESOLUTION OF REMOTE SENSING IMAGES BASED ON TRANSFERR...

引用

IEEE International geoscience and Remote Sensing Symposium

作者： Wen Ma Zongxu Pan Jiayi Guo Bin Lei Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China

Single image super-resolution (SR) has been widely studied in recent years as a crucial technique for remote sensing applications. This paper proposes a SR method for remote sensing images based on a transferred generative adversarial network (TGAN). Different from the previous GAN-based SR approaches, the novelty of our method mainly reflects from two aspects. First, the batch normalization layers are removed to reduce the memory consumption and the computational burden, as well as raising the accuracy. Second, our model is trained in a transfer-learning fashion to cope with the insufficiency of training data, which is the crux of applying deep learning methods to remote sensing applications. The model is firstly trained on an external dataset DIV2K and further fine-tuned with the remote sensing dataset. Our experimental results demonstrate that the proposed method is superior to SRCNN and SRGAN in terms of both the objective evaluation and the subjective perspective.

关键词： Remote sensing images Super-resolution Generative adversarial network Transfer learning

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International geoscience and Remote Sensing Symposium

作者： Feng Wang Yuming Xiang Xinghui Yao Jiayin Liu Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China

The conventional shape similarity measurements of remote sensing data face problems in the situation of noise interference, partial information occlusion and missing. A method of shape similarity measurement based on principal curvature enhancement distance transformation is proposed. The distance transformation is carried out to extend the range of the shape contour, improving the robustness of the similarity measure. Besides, to ensure the accuracy of measurement results, the distance map is enhanced by the principal curvature of the shape contour, improving the response of contours with rich information. application experiments of road vectors with GPS data and optical remote sensing images show that the method is effective in practical application.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAR TARGET CLASSIFICATION WITH CYCLEGAN TRANSFERRED SIMULATED SAMPLES

SAR TARGET CLASSIFICATION WITH CYCLEGAN TRANSFERRED SIMULATE...

引用

IEEE International geoscience and Remote Sensing Symposium

作者： Lei Liu Zongxu Pan Xiaolan Qiu Lingxiao Peng Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China

Target classification is an important part in automatic target recognition (ATR) systems. Deep learning methods get state of the art performance in SAR target classification. Simulation is a useful data augmentation method when the numbers of real samples for training is not sufficient. This article discusses how to release the full potential of simulated samples which is used to improve performance of SAR target classifier. The proposed method is based on cycle adversarial network (CycleGAN), which can transfer simulated samples to be more similar with real samples in image domain. Experiments show that adding simulated samples straightforward into training dataset is not helpful to improve the performance. However, adding the transferred simulated samples for training results in about 10% increase in accuracy in the designed SAR airplane classification experiment, compared with training without data augmentation.

关键词： Training Testing Synthetic aperture radar Azimuth Gallium nitride Data models Airplanes

来源：评论

学校读者我要写书评

暂无评论

Curved-path SAR geolocation error analysis based on BP algorithm 38

Curved-path SAR geolocation error analysis based on BP algor...

引用

38th Annual IEEE International geoscience and Remote Sensing Symposium, IGARSS 2018

作者： Liu, Junbin Qiu, Xiaolan Huang, Lijia Ding, Chibiao Liu, Ming University of Chinese Academy of Sciences China Key Laboratory of Technology in Geo-spatial Information Processing and Application System CAS China Institute of Electronics Chinese Academy of Sciences China National Disaster Reduction Center Ministry of Civil Affairs NDRCC China

ISBN: (纸本)9781538671504

The theoretical modeling and analysis of SAR location error play an important role in SAR system design and error source budget. Existing SAR geolocation error models are mainly implicit, which are not easy to do analysis, especially in the curved-path case. In this paper, a theoretical explicit model of the relationship between image geolocation error and the path measurement error is established for curved-path SAR, based on BP imaging algorithm. Simulations are given which verify the correctness of the model. The explicit model and the analysis results provide an effective reference for understanding and budgeting the system-level geometric location error for curved-path SAR, such as geoSAR. © 2018 IEEE

关键词： geology Imaging Synthetic aperture radar Trajectory Mathematical model Analytical models Simulation

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal dynamics of coastal dead zones in the Gulf of Mexico over 20 years using remote sensing

引用

Science of the Total Environment 2025年 979卷

作者： Li, Yingjie Xia, Zilong Nguyen, Lan Wan, Ho Yi Wan, Luwen Wang, Mengqiu Jia, Nan Matli, Venkata Rohith Reddy Li, Yi Seeley, Megan Moran, Emilio F. Liu, Jianguo Center for Systems Integration and Sustainability Department of Fisheries and Wildlife Michigan State University East LansingMI48823 United States Environmental Science and Policy Program Michigan State University East LansingMI48823 United States Natural Capital Project Woods Institute for the Environment Doerr School of Sustainability Stanford University StanfordCA94305 United States Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology Key Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources School of Geography and Ocean Science Nanjing University Jiangsu Nanjing210023 China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Jiangsu Nanjing210023 China Department of Biological Sciences University of Calgary CalgaryABT2N 1N4 Canada Department of Wildlife California State Polytechnic University Humboldt ArcataCA95521 United States Department of Wildlife Ecology and Conservation University of Florida GainesvilleFL32611 United States Department of Earth System Science Stanford University StanfordCA94305 United States Earth and Environmental Sciences Michigan State University East LansingMI48824 United States School of Remote Sensing and Information Engineering Wuhan University Wuhan430072 China Department of Earth Sciences The University of Hong Kong Hong Kong 999077 China Center for Geospatial Analytics North Carolina State University RaleighNC27607 United States College of the Environment and Ecology Xiamen University Xiamen361102 China School of Geographical Sciences and Urban Planning Arizona State University TempeAZ85281 United States Center for Global Discovery and Conservation Science Arizona State University TempeAZ85281 United States Center for Global Change and Earth Observations Michigan State University East LansingMI48824 United States Department of Geography Environment and Spatial Science

Spreading marine dead zones (or hypoxia) are threatening coastal ecosystems and affecting billions of people's livelihoods globally. However, the lack of field observations makes it challenging to estimate dead zones with spatial precision and across large scales. While satellites offer great potential for detecting environmental changes through large-scale and temporal consistent data, they have yet to be fully integrated into the spatio-temporal dynamic mapping of hypoxia. To address this limitation, we integrated satellite imagery with field observations in random forest models on the Google Earth Engine platform to characterize dead zone dynamics from 2000 to 2019. We applied the workflow to the Gulf of Mexico, which has the largest dead zones in North America. Our model explained 64 % (± 5 %) of the variance in predicting dead zones using satellite data. The analysis revealed that dead zones in the Gulf peaked in 2009 (17,699 ± 679 km2) and contracted afterward in terms of both size and persistence (% days with hypoxia). Despite this contraction, the average size between 2010 and 2019 was twice that of the coastal reduction goal (2) set by the Gulf of Mexico Hypoxia Task Force. Furthermore, dead zones occurred more frequently in the western Gulf, and nearly half of the western region experienced dead zones annually. In addition to inter-annual changes, our analysis highlighted the intra-annual dynamics of this phenomenon. Notably, dead zones expanded in June, peaking in size from mid-August to early September. The high temporal and spatial resolution of this dataset allows policymakers to develop targeted management plans and environmental policies. Our approach, which incorporates remote sensing for long-term monitoring of coastal dead zones, can be applied to worldwide monitoring initiatives when paired with local field observations. © 2025 Elsevier B.V.

关键词： Eutrophication

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network-Based Residue Super-Resolution for Video Coding

Convolutional Neural Network-Based Residue Super-Resolution ...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Kang Liu Dong Liu Houqiang Li Feng Wu CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781538644591;9781538644584

Inspired by the progress of image and video super-resolution (SR) achieved by convolutional neural network (CNN), we propose a CNN-based residue SR method for video coding. Different from the previous works that operate in the pixel domain, i.e. down- and up-sampling of image or video frame, we propose to perform down- and up-sampling in the residue domain. Specifically, for each block, we perform motion estimation and compensation to achieve residual signal at the original resolution, then we down-sample the residue and compress it at low resolution, and perform residue SR using a trained CNN model. We design a new CNN for residue SR with the help of the motion compensated prediction signal. We integrate the residue SR method into the High Efficiency Video Coding (HEVC) scheme, providing mode decision at the level of coding tree unit. Experimental results show that our method achieves on average 4.0% and 2.8% BD-rate reduction under low-delay P and low-delay B configurations, respectively.

关键词： Encoding Signal resolution Video coding spatial resolution Delays Convolution

来源：评论

学校读者我要写书评

暂无评论

SDM: Semantic Distortion Measurement for Video Encryption

SDM: Semantic Distortion Measurement for Video Encryption

引用

International Conference on Automatic Face and Gesture Recognition

作者： Yongquan Hu Wei Zhou Shuxin Zhao Zhibo Chen Weiping Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

Semantic information is important in video encryption. However, existing image quality assessment (IQA) methods, such as the peak signal to noise ratio (PSNR), are still widely applied to measure the encryption security. Generally, these traditional IQA methods aim to evaluate the image quality from the perspective of visual signal rather than semantic information. In this paper, we propose a novel semantic-level full-reference image quality assessment (FR-IQA) method named Semantic Distortion Measurement (SDM) to measure the degree of semantic distortion for video encryption. Then, based on a semantic saliency dataset, we verify that the proposed SDM method outperforms state-of-the-art algorithms. Furthermore, we construct a Region Of Semantic Saliency (ROSS) video encryption system to demonstrate the effectiveness of our proposed SDM method in the practical application.

关键词： Semantics Encryption Distortion Distortion measurement Visualization Object segmentation

来源：评论

学校读者我要写书评

暂无评论

Multiscale Progressive Image Compression Network Guided by Learnable Just Noticeable Distortion

Multiscale Progressive Image Compression Network Guided by L...

引用

IEEE Visual Communications and Image processing (VCIP)

作者： Xin Jin Runchun Ye Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781538644591;9781538644584

One key challenge to the learning-based image compression is that adaptive bit allocation is crucial for compression effectiveness but can hardly be trained into a neural network. Hereby, in this work, We presents an end-to-end trainable image compression framework, named Multi-scale Progressive Network (MPN) to achieve spatially variant bit allocation and rate control through the guidance of a novel learnable just noticeable distortion (JND) map. Specifically, MPN's encoder archives multi-scale feature representation through a three-branched structure. Each branch employs an independent feature extraction strategy for the specific receptive field and merge progressively under the guidance of corresponding learnable JND maps that generated by our proposed Bit-Allocation sub-Network (BAN), which make MPN focus on the areas where attract the human visual system (HVS) and preserve more texture of the image during the compression procedure. Finally, a hybrid objective function is introduced to further make MPN more efficient and mimic the discriminative characteristics of the human visual system (HVS). Experiments show that MPN significantly outperforms traditional JPEG, JPEG 2000 and few state-of-art learning-based methods by multi-scale structural similarity (MS-SSIM) index, and has the ability to produce the much better visual result with rich textures, sharp edges, and fewer artifacts.

关键词： Image coding Feature extraction Transform coding Distortion Image reconstruction Bit rate Visualization

来源：评论

学校读者我要写书评

暂无评论

LEARNED SCALABLE IMAGE COMPRESSION WITH BIDIRECTIONAL CONTEXT DISENTANGLEMENT NETWORK

arXiv

引用

arXiv 2018年

作者： Zhang, Zhizheng Chen, Zhibo Lin, Jianxin Li, Weiping CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt bit-plane decomposition to decompose the information coarsely before the deep-learning-based transformation. However, the information carried by different bit-planes is not only unequal in entropy but also of different importance for reconstruction. We thus take the hidden features corresponding to different bit-planes as the context and design a network topology with bidirectional flows to disentangle the contextual information for more effective compressed representations. Our proposed scheme enables us to obtain the compressed codes with scalable rates via a one-pass encoding-decoding. Experiment results demonstrate that our proposed model outperforms the state-of-the-art DNN-based scalable image compression methods in both PSNR and MS-SSIM metrics. In addition, our proposed model achieves better performance in MS-SSIM metric than conventional scalable image codecs. Effectiveness of our technical components is also verified through sufficient ablation experiments. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

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：