检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ketan Tang Oscar C. Au Lu Fang Jiahao Pang Yuanfang Guo Jiali Li The Hong Kong University of Science and Technology CAS Key Laboratory of Technology in Geo-spatial Information Processingand Application System University of Science and Technology of China

Subpixel-based downsampling has shown its advantages over pixel-based downsampling in terms of preserving more spatial details along edges and generating sharper images, at the cost of certain amount of color-fringing artifacts in the downsampled image. To balance the sharpness and color-fringing artifacts, some algorithms are proposed to design optimal anti-aliasing (AA) filters, which are either image independent, or computationally too expensive. And all of the existing AA filters are designed for fixed downsampling factor, which makes them impractical for real applications. In this paper we propose two fast algorithms to design AA filter for arbitrary factor subpixel downsampling based on frequency analysis of the input image. The proposed algorithms generate image dependent AA filter which is as good as the state-of-the-art algorithm, but much faster.

关键词： Algorithm design and analysis Cutoff frequency Shape Frequency-domain analysis Interpolation Signal processing algorithms Time measurement

来源：评论

学校读者我要写书评

暂无评论

RELAXATION LABELLING BASED LAND MASKING IN SAR IMAGES

RELAXATION LABELLING BASED LAND MASKING IN SAR IMAGES

引用

IEEE International Geoscience and Remote Sensing Symposium

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

In this paper, a relaxation labelling based land masking method is proposed for separating sea and land in SAR images. Land masking, also known as sea-land segmentation, is a part of ship detection system for SAR images to avoid detecting false alarms in the land. Relaxation labeling is an iterative method, which can separate foreground pixels from background ones using the neighborhood information of pixels in the image. When relaxation labelling converges, the segmented result is often unsatisfactory, since it tends to label more foreground pixels. To overcome this issue, a loss composed of the background probability distribution diversity and the gradient magnitude of the result is introduced to indicate when to stop the iteration. Experimental results on several Gaofen-3 SAR images demonstrate the effectiveness of the proposed method.

关键词： Labeling Image segmentation Synthetic aperture radar Marine vehicles Probability distribution Morphology Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A novel methodology for calculating the aerosol direct radiative effect using a non-uniform five-dimensional lookup table (Dec, 10.1080/01431161.2023.2295833, 2023)

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2024年第3期45卷 0i-0i页

作者： Shi, Zhenwei Xu, Ning Li, Jianzhong Zhang, Zhaoxu Zhao, Hui Longa, Hui Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing China School of Environmental Science and Engineering Tiangong University Tianjin China Surveying and Mapping Geographic Information Center Geological Brigade of Shandong Nuclear Industry Qingdao Shandong China

The quantification of aerosol direct radiative effects (ADREs) under clear sky conditions is essential for understanding the influence of aerosols on climate. This paper introduces a novel approach, the non-uniform five-dimensional lookup table (NU-5D-LUT) method, for calculating the ADREs under clear sky conditions. The NU-5D-LUT method considers key parameters such as aerosol optical thickness, single scattering albedo, asymmetry factor, surface albedo, and solar zenith angle. Validation against the SBDART model shows strong agreement, with correlation coefficients of 0.97 and 0.99 for TOA and BOA ADREs, respectively. Global comparisons demonstrate consistent ADRE distributions, with relative errors below 5.8% for TOA ADRE and 4.4% for BOA ADRE. The NU-5D-LUT method significantly reduces computation time, offering a practical solution for large-scale simulations and climate model evaluations in aerosol research.

关键词： Aerosol direct radiative effect aerosol optical properties lookup table

来源：评论

学校读者我要写书评

暂无评论

Improving resistance to adversarial deformations by regularizing gradients

arXiv

引用

arXiv 2020年

作者： Xia, Pengfei Li, Bin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems Department of Electronic Engineering and Information Science University of Science of Technology of China Hefei China

Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. Currently, most defense methods are designed to defend against additive noise attacks, their performance cannot be guaranteed when against non-additive noise attacks. In this paper, we focus on adversarial deformations, a typical class of non-additive noise attacks, and propose a flow gradient regularization with random start to improve the resistance of models. Theoretically, we prove that, compared with input gradient regularization, regularizing flow gradients is able to get a tighter bound. Across multiple datasets, architectures, and adversarial deformations, our experimental results consistently indicate that models trained with flow gradient regularization can acquire a better resistance than trained with input gradient regularization with a large margin. Moreover, compared with adversarial training, our method can achieve better results in optimization-based and gradient-free attacks, and combining these two methods can improve the resistance against deformation attacks further. Finally, we give a unified form of gradient regularization, which can be used to derive the corresponding form when facing other types of attack. Copyright © 2020, The Authors. All rights reserved.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

Automated ortho-rectified SAR image of GF-3 satellite using Reverse-Range-Doppler method

Automated ortho-rectified SAR image of GF-3 satellite using ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jiayin Liu Xiaolan Qiu Wen Hong Institute of Electronics Chinese Academy of Sciences Beijing China Key Laboratory of Technology on Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China National Key Laboratory of Microwave Imaging Technology Beijing China

GF-3 is the Chinese Synthetic Aperture Radar (SAR) satellite mission with scientific and commercial applications, which will be launched in 2016. The ortho-rectification image combined with the DEM data can only be satisfied with the applications of the high resolution radar image, the data quantity with wide-breadth also put forward higher request to the automation processing. The Reverse-Range-Doppler method was used to ortho-rectified the SAR image of GF-3 satellite based on the Range-Doppler model in this paper. It not only ensures the correction precision, but also simplifies the iteration steps about DEM data, and improves the efficiency of automatic processing.

关键词： Synthetic aperture radar Mathematical model Satellites Doppler effect Space vehicles Earth Azimuth

来源：评论

学校读者我要写书评

暂无评论

HIGH QUALITY REMOTE SENSING IMAGE SUPER-RESOLUTION USING DEEP MEMORY CONNECTED NETWORK

HIGH QUALITY REMOTE SENSING IMAGE SUPER-RESOLUTION USING DEE...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Wenjia Xu Guangluan Xu Yang Wang Xian Sun Daoyu Lin Yirong Wu Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China

Single image super-resolution is an effective way to enhance the spatial resolution of remote sensing image, which is crucial for many applications such as target detection and image classification. However, existing methods based on the neural network usually have small receptive fields and ignore the image detail. We propose a novel method named deep memory connected network (DMCN) based on a convolutional neural network to reconstruct high-quality super-resolution images. We build local and global memory connections to combine image detail with environmental information. To further reduce parameters and ease time-consuming, we propose down-sampling units, shrinking the spatial size of feature maps. We test DMCN on three remote sensing datasets with different spatial resolution. Experimental results indicate that our method yields promising improvements in both accuracy and visual performance over the current state-of-the-art.

关键词： spatial resolution Remote sensing Image reconstruction Training Convolutional neural networks Satellites

来源：评论

学校读者我要写书评

暂无评论

Cut-and-Fold: Automatic 3D modeling from a single image

Cut-and-Fold: Automatic 3D modeling from a single image

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Guihang Wang Xuejin Chen Si Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui China University of California San Diego La Jolla California USA

ISBN: (纸本)9781479947164

This paper presents a novel approach to automatically generate a plausible 3D model from a single outdoor image. Outdoor scene can be modeled as a set of planar billboards such as ground, sky and vertical trees or buildings. This Cut-and-Fold system takes the advantages of the statistical classification method for high-level geometric labeling of the image regions and the automatic image segmentation algorithm for detailed boundaries of the geometric regions to generate accurate geometric labeling and realistic rendering of novel views. Taking a single image as input, our method first roughly classifies each sub-region to the geometric categories: vertical, ground or sky. Then image segmentation algorithm is employed to refine the labeling results and generate accurate boundaries for the geometric regions. After cutting the image into several regions with their geometric labels, the system folds the regions into 3D billboards with accurate boundaries. The experimental results demonstrate that our method is capable of creating plausible 3D models automatically for a wide range of outdoor scenes.

关键词： Image segmentation Abstracts Labeling Indium phosphide Three-dimensional displays Solid modeling

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Single-polarized and Polarimetric SAR Images Applied on Unsupervised Classification

A Comparative Study of Single-polarized and Polarimetric SAR...

引用

IEEE International Conference on Radar

作者： Junrong Qu Xiaolan Qiu Key Laboratory of Technology in Geo-spatial Information and Application System Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information and Application System Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665468893

SAR image understanding is a significant but also challenging issue in practice. In order to detect the difference between single-polarized and polarimetric SAR (PolSAR) data and explore more information from the pre one, we use GF3 data for experiments and adopt the Deep Clustering with Convolutional Autoencoders (DCEC) algorithm for single-polarized SAR image unsupervised classification. Using both the Kappa coefficient and mutual information derived from the confusion matrix, the results of single-polarized SAR data and PolSAR data are compared. It shows that the classification results of single-polarized SAR data match with the polarimetric ones to some extent, and their results are comparable in some specific applications. This paper presents the potential of information mining from single-polarized SAR images, as well as gives some references for the selection and trade-off between single- and full-polarized SAR data.

关键词： Image resolution Correlation Clustering algorithms Scattering Radar imaging Radar polarimetry Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Sequential reinforced 360-degree video adaptive streaming with cross-user attentive network

arXiv

引用

arXiv 2020年

作者： Fu, Jun Chen, Zhibo Chen, Xiaoming Li, Weiping CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China School of Computer Science and Engineering Beijing Technology and Business University China

In the tile-based 360-degree video streaming, predicting user’s future viewpoints and developing adaptive bitrate (ABR) algorithms are essential for optimizing user’s quality of experience (QoE). Traditional single-user based viewpoint prediction methods fail to achieve good performance in long-term prediction, and the recently proposed reinforcement learning (RL) based ABR schemes applied in traditional video streaming can not be directly applied in the tile-based 360-degree video streaming due to the exponential action space. Therefore, we propose a sequential reinforced 360-degree video streaming scheme with cross-user attentive network. Firstly, considering different users may have the similar viewing preference on the same video, we propose a cross-user attentive network (CUAN), boosting the performance of long-term viewpoint prediction by selectively utilizing cross-user information. Secondly, we propose a sequential RL-based (360SRL) ABR approach, transforming action space size of each decision step from exponential to linear via introducing a sequential decision structure. We evaluate the proposed CUAN and 360SRL using trace-driven experiments and experimental results demonstrate that CUAN and 360SRL outperform existing viewpoint prediction and ABR approaches with a noticeable margin. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Close Look at Few-shot Real Image Super-resolution from the Distortion Relation Perspective

arXiv

引用

arXiv 2021年

作者： Li, Xin Jin, Xin Fu, Jun Yu, Xiaoyuan Tong, Bei Chen, Zhibo The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The Eastern Institute for Advanced Study China Huawei Cloud China

Collecting amounts of distorted/clean image pairs in the real world is non-trivial, which seriously limits the practical applications of these supervised learning-based methods on real-world image super-resolution (RealSR). Previous works usually address this problem by leveraging unsupervised learning-based technologies to alleviate the dependency on paired training samples. However, these methods typically suffer from unsatisfactory texture synthesis due to the lack of supervision of clean images. To overcome this problem, we are the first to have a close look at the under-explored direction for RealSR, i.e., few-shot real-world image super-resolution, which aims to tackle the challenging RealSR problem with few-shot distorted/clean image pairs. Under this brand-new scenario, we propose Distortion Relation guided Transfer Learning (DRTL) for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions (i.e., synthetic distortions) to the target RealSR under the guidance of distortion relation. Concretely, DRTL builds a knowledge graph to capture the distortion relation between auxiliary distortions and target distortion (i.e., real distortions in RealSR). Based on the distortion relation, DRTL adopts a gradient reweighting strategy to guide the knowledge transfer process between auxiliary distortions and target distortions. In this way, DRTL could quickly learn the most relevant knowledge from the synthetic distortions for the target distortion. We instantiate DRTL with two commonly-used transfer learning paradigms, including pre-training and meta-learning pipelines, to realize a distortion relation-aware Few-shot RealSR. Extensive experiments on multiple benchmarks and thorough ablation studies demonstrate the effectiveness of our DRTL. Copyright © 2021, The Authors. All rights reserved.

关键词： Textures

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：