检索结果-内蒙古大学图书馆

Temporal Context Mining for Learned Video Compression

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sheng, Xihua Li, Jiahao Li, Bin Li, Li Liu, Dong Lu, Yan The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China Microsoft Research Asia Beijing100080 China

Applying deep learning to video compression has attracted increasing attention in recent few years. In this work, we address end-to-end learned video compression with a special focus on better learning and utilizing temporal contexts. We propose to propagate not only the last reconstructed frame but also the feature before obtaining the reconstructed frame for temporal context mining. From the propagated feature, we learn multi-scale temporal contexts and re-fill the learned temporal contexts into the modules of our compression scheme, including the contextual encoder-decoder, the frame generator, and the temporal context encoder. We discard the parallelizationunfriendly auto-regressive entropy model to pursue a more practical encoding and decoding time. Experimental results show that our proposed scheme achieves a higher compression ratio than the existing learned video codecs. Our scheme also outperforms x264 and x265 (representing industrial software for H.264 and H.265, respectively) as well as the official reference software for H.264, H.265, and H.266 (JM, HM, and VTM, respectively). Specifically, when intra period is 32 and oriented to PSNR, our scheme outperforms H.265-HM by 14.4% bit rate saving;when oriented to MS-SSIM, our scheme outperforms H.266-VTM by 21.1% bit rate saving. Copyright © 2021, The Authors. All rights reserved.

关键词： Image compression

A FEATURE ENHANCEMENT METHOD BASED ON THE SUB-APERTURE DECOMPOSITION FOR ROTATING FRAME SHIP DETECTION IN SAR IMAGES

学校读者我要写书评

暂无评论

A FEATURE ENHANCEMENT METHOD BASED ON THE SUB-APERTURE DECOM...

2021 IEEE International geoscience and Remote Sensing Symposium, IGARSS 2021

作者： Lei, Songlin Qiu, Xiaolan Ding, Chibiao Lei, Shujie National Key Laboratory of Microwave Imaging Technology Beijing100190 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Shanghai Radio Equipment Research Institute Shanghai201100 China

ISBN: (纸本)9781665403696

Deep learning algorithms are widely used in SAR target detection. At present, most detection methods based on neural networks treat SAR images as optical images for processing, and do not fully exploit the characteristics of SAR images. In this paper, a method for feature enhancement using sub-aperture decomposition is proposed. Considering the advantages of the rotate box in eliminating interference, we conducted experiments on the rotating frame detection network Rotate RetinaNet using the Complex SAR images Rotation Ship Detection Dataset (CSRSDD). Compared with the base method, AP improves by 2.4% without bells and whistles. The results confirm the effectiveness of the proposed method. © 2021 IEEE

关键词： Neural networks Optical computing Object detection Optical fiber networks Optical detectors Optical imaging Radar polarimetry

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

学校读者我要写书评

暂无评论

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

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

Efficient Sparse MIMO SAR Imaging with Fast Iterative Method Based on Back Projection and Approximated Observation

学校读者我要写书评

暂无评论

Efficient Sparse MIMO SAR Imaging with Fast Iterative Method...

Electronics and Electrical Engineering technology (EEET), International Conference on

作者： Pengyu Jiang Zhe Zhang Bingchen Zhang Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Suzhou Aerospace Information Research Institute Suzhou China

Compressed sensing technique is widely used in the field of multiple input multiple output (MIMO) radar imaging to suppress sidelobes and noise, bringing better imaging performance. However, many constraints are introduced to the sparse reconstruction model, current sparse microwave imaging model is based on several assumptions, such as far field assumption, which might not hold in some circumstances. In this paper, a novel two-dimensional sparse reconstruction method based on approximated observation is proposed. First, we obtain the measurement matrix by the inverse back-projection operator, and construct a two-dimensional sparse reconstruction model. Then, we adopt the minimax concave constraint as the regularization term and use the iterative soft threshold algorithm (ISTA) for sparse reconstruction. The method retains the advantages of the BP algorithm and the sparse reconstruction algorithm at the same time, and the distance between the target and the antenna array is not constrained by image reconstruction performance of the sparse reconstruction algorithm. Simulations and experiments demonstrate the effectiveness of the proposed method.

关键词： MIMO radar Simulation Imaging Radar imaging Reconstruction algorithms Sparse matrices Velocity measurement

No-reference quality assessment for 360-degree images by analysis of multi-frequency information and local-global naturalness

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Wei Xu, Jiahua Jiang, Qiuping Chen, Zhibo CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China School of Information Science and Engineering Ningbo University Ningbo315211 China

360-degree/omnidirectional images (OIs) have achieved remarkable attentions due to the increasing applications of virtual reality (VR). Compared to conventional 2D images, OIs can provide more immersive experience to consumers, benefitting from the higher resolution and plentiful field of views (FoVs). Moreover, observing OIs is usually in the head mounted display (HMD) without references. Therefore, an efficient blind quality assessment method, which is specifically designed for 360-degree images, is urgently desired. In this paper, motivated by the characteristics of the human visual system (HVS) and the viewing process of VR visual contents, we propose a novel and effective no-reference omnidirectional image quality assessment (NR OIQA) algorithm by Multi-Frequency information and Local-Global Naturalness (MFILGN). Specifically, inspired by the frequency-dependent property of visual cortex, we first decompose the projected equirectangular projection (ERP) maps into wavelet subbands by using discrete Haar wavelet transform (DHWT). Then, the entropy intensities of low-frequency and high-frequency subbands are exploited to measure the multi-frequency information of OIs. Besides, except for considering the global naturalness of ERP maps, owing to the browsed FoVs, we extract the natural scene statistics (NSS) features from each viewport image as the measure of local naturalness. With the proposed multi-frequency information measurement and local-global naturalness measurement, we utilize support vector regression (SVR) as the final image quality regressor to train the quality evaluation model from visual quality-related features to human ratings. To our knowledge, the proposed model is the first no-reference quality assessment method for 360-degreee images that combines multi-frequency information and image naturalness. Experimental results on two publicly available OIQA databases demonstrate that our proposed MFILGN outperforms state-of-the-art full-reference (FR) a

关键词： Helmet mounted displays

ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Muhan Zhang, Zhe Qiu, Xiaolan Gao, Silin Wang, Yue Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology China Suzhou Aerospace Information Research Institute Jiangsu Suzhou China Aerospace Information Research Institute Chinese Academy of Sciences China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China The Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Electrical and Computer Engineering Department George Mason University FairfaxVA United States

Tomographic SAR technique has attracted remarkable interest for its ability of three-dimensional resolving along the elevation direction via a stack of SAR images collected from different cross-track angles. The emerged compressed sensing (CS)-based algorithms have been introduced into TomoSAR considering its super-resolution ability with limited samples. However, the conventional CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity, and complex parameter fine-tuning. Aiming at efficient TomoSAR imaging, this paper proposes a novel efficient sparse unfolding network based on the analytic learned iterative shrinkage thresholding algorithm (ALISTA) architecture with adaptive threshold, named Adaptive Threshold ALISTA-based Sparse Imaging Network (ATASI-Net). The weight matrix in each layer of ATASI-Net is pre-computed as the solution of an offline optimization problem, leaving only two scalar parameters to be learned from data, which significantly simplifies the training stage. In addition, adaptive threshold is introduced for each azimuth-range pixel, enabling the threshold shrinkage to be not only layer-varied but also element-wise. Moreover, the final learned thresholds can be visualized and combined with the SAR image semantics for mutual feedback. Finally, extensive experiments on simulated and real data are carried out to demonstrate the effectiveness and efficiency of the proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

Intertidal area classification with generalized extreme value distribution and Markov random field in quad-polarimetric synthetic aperture radar imagery

学校读者我要写书评

暂无评论

Frontiers of information technology & Electronic Engineering 2019年第2期20卷 253-264页

作者： Ting-ting JIN Xiao-qiang SHE Xiao-lan QIU Bin LEI Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of ElectronicsChinese Academy of Sciences University of Chinese Academy of Sciences Huawei Software Technologies Co. Ltd.

Classification of intertidal area in synthetic aperture radar(SAR) images is an important yet challenging issue when considering the complicatedly and dramatically changing features of tidal fluctuation. The difficulty of intertidal area classification is compounded because a high proportion of this area is frequently flooded by water, making statistical modeling methods with spatial contextual information often ineffective. Because polarimetric entropy and anisotropy play significant roles in characterizing intertidal areas, in this paper we propose a novel unsupervised contextual classification algorithm. The key point of the method is to combine the generalized extreme value(GEV) statistical model of the polarization features and the Markov random field(MRF) for contextual smoothing. A goodness-of-fit test is added to determine the significance of the components of the statistical model. The final classification results are obtained by effectively combining the results of polarimetric entropy and anisotropy. Experimental results of the polarimetric data obtained by the Chinese Gaofen-3 SAR satellite demonstrate the feasibility and superiority of the proposed classification algorithm.

关键词： Intertidal classification Polarimetric synthetic aperture radar Finite mixture model Markov random field Generalized extreme value model

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

学校读者我要写书评

暂无评论

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

GRIDLESS TOMOGRAPHIC SAR IMAGING BASED ON ACCELERATED ATOMIC NORM MINIMIZATION WITH EFFICIENCY

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Gao, Silin Zhang, Zhe Zhang, Bingchen Wu, Yirong Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou215123 China Suzhou Aerospace Information Research Institute Suzhou215123 China

Synthetic aperture radar (SAR) tomography (TomoSAR) enables the reconstruction and three-dimensional (3D) localization of targets based on multiple two-dimensional (2D) observations of the same scene. The resolving along the elevation direction can be treated as a line spectrum estimation problem. However, traditional super-resolution spectrum estimation algorithms require multiple snapshots and uncorrelated targets. Meanwhile, as the most popular TomoSAR imaging method in modern years, compressed sensing (CS) based methods suffer from the gridding mismatch effect which markedly degrades the imaging performance. As a gridless CS approach, atomic norm minimization can avoid the gridding effect but requires enormous computing resources. Addressing the above issues, this paper proposes an improved fast ANM algorithm to TomoSAR elevation focusing by introducing the IVDST-ANM algorithm, which reduces the huge computational complexity of the conventional time-consuming semi-positive definite programming (SDP) by the iterative Vandermonde decomposition and shrinkage-thresholding (IVDST) approach, and retains the benefits of ANM in terms of gridless imaging and single snapshot recovery. We conducted experiments using simulated data to evaluate the performance of the proposed method, and reconstruction results of an urban area from the SARMV3D-Imaging 1.0 dataset are also presented. Copyright © 2022, The Authors. All rights reserved.

关键词： Compressed sensing