检索结果-内蒙古大学图书馆

DeepEraser: Deep Iterative Context Mining for Generic Text Eraser

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Feng, Hao Wang, Wendi Liu, Shaokai Deng, Jiajun Zhou, Wengang Li, Houqiang The CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China The University of Adelaide Australian Institute for Machine Learning Australia

In this work, we present DeepEraser, an effective deep network for generic text removal. DeepEraser utilizes a recurrent architecture that erases the text in an image via iterative operations. Our idea comes from the process of erasing pencil script, where the text area designated for removal is subject to continuous monitoring and the text is attenuated progressively, ensuring a thorough and clean erasure. Technically, at each iteration, an innovative erasing module is deployed, which not only explicitly aggregates the previous erasing progress but also mines additional semantic context to erase the target text. Through iterative refinements, the text regions are progressively replaced with more appropriate content and finally converge to a relatively accurate status. Furthermore, a custom mask generation strategy is introduced to improve the capability of DeepEraser for adaptive text removal, as opposed to indiscriminately removing all the text in an image. Our DeepEraser is notably compact with only 1.4M parameters and trained in an end-to-end manner. To verify its effectiveness, extensive experiments are conducted on several prevalent benchmarks, including SCUT-Syn, SCUT-EnsText, and Oxford Synthetic text dataset. The quantitative and qualitative results demonstrate the effectiveness of our DeepEraser over the state-of-the-art methods, as well as its strong generalization ability in custom mask text removal. The codes and pre-trained models are available at https://***/fh2019ustc/DeepEraser Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

Vibration Error Compensation Imaging Algorithm for Arc Array SAR Besed on Parameter Estimation

学校读者我要写书评

暂无评论

Vibration Error Compensation Imaging Algorithm for Arc Array...

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Yifan Dong Congfei Wu Wei Xu Pingping Huang Weixian Tan Wen Hong Inner Mongolia Key Laboratory of Radar Technology and Application Hohhot China Key Laboratory of Technology in Geospatial Information Processing and Application System Beijing Chian

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

Arc array synthetic aperture radar (SAR) is a novel array imaging system for wide-area observation, with wide observation range and high resolution. Arc array synthetic aperture radar uses W-band as carrier signal, and W-band wavelength is short. The small high-frequency vibration of the helicopter-borne platform will cause significant changes in the phase of the echo signal, which will seriously deteriorate the imaging performance of arc array synthetic aperture radar. Based on the high order approximate imaging algorithm of arc array radar, this paper proposes a vibration phase error compensation imaging algorithm based on Short-time Fourier transform (STFT) parameter estimation. The algorithm uses the high-order approximation imaging algorithm of curved array radar to perform high-order approximation of the slant range model, compensates the range cell migration (RCM) and range azimuth coupling in the two-dimensional frequency domain, and finally realizes the vibration error compensation in the range Doppler domain. The simulation results of the lattice target verify the effectiveness of the imaging method.

关键词：

A visually inspired variational method for automatic image registration

学校读者我要写书评

暂无评论

Cehui Xuebao/Acta geodaetica et Cartographica Sinica 2015年第8期44卷 893-899页

作者： Wang, Huixian Jin, Huijia Lei, Chengqiang Jiang, Wanshou Wang, Yan Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China Electronic & Optical Engineering Department Mechanical Engineering College Shijiazhuang050003 China Institute of Information in Remote Sensing in Beijing Beijing100192 China

A visually inspired variational method for automatic image registration is proposed to solve local deformation which traditional global registration model cannot well satisfy. The variational model considers local transformation, global smoothness and visual constraints. To account for intensity variations, we incorporate change of local contrast and brightness into our model. Firstly, the data entry of registration model is built according to the root-mean-square error of intensity;secondly, adaptive constraint using H1 half norm is used to ensure the global smooth in the model;finally, in order to make sure that the spatial attributes of the image satisfy the visual requirements and without distortion, the linear features are used as priori constraints. During the solution of model parameters, the whole image is used to globally estimate the transformation parameters, and then local estimation of the parameters is taken in a small neighbor. The entire procedure is built upon a multi-level differential framework, and the transformation parameters are calculated iteratively, which can consider both global smoothness and local distortion. To assess the quality of the proposed method, ZY-3 satellite images were used. Visual and quantitative analysis proved that the proposed method can significantly improve the registration precision. ©, 2015, SinoMaps Press. All right reserved.

关键词： Image registration

Prior-enlightened and motion-robust video deblurring

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhou, Ya Xu, Jianfeng Tasaka, Kazuyuki Chena, Zhibo Li, Weiping CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230026 China KDDI Research Inc. Fujimino-shi Saitama356-8502 Japan

Various blur distortions in video will cause negative impact on both human viewing and video-based applications, which makes motion-robust deblurring methods urgently needed. Most existing works have strong dataset dependency and limited generalization ability in handling challenging scenarios, like blur in low contrast or severe motion areas, and non-uniform blur. Therefore, we propose a PRiOr-enlightened and MOTION-robust video deblurring model (PROMOTION) suitable for challenging blurs. On the one hand, we use 3D group convolution to efficiently encode heterogeneous prior information, explicitly enhancing the scenes’ perception while mitigating the output’s artifacts. On the other hand, we design the priors representing blur distribution, to better handle non-uniform blur in spatio-temporal domain. Besides the classical camera shake caused global blurry, we also prove the generalization for the downstream task suffering from local blur. Extensive experiments demonstrate we can achieve the state-of-the-art performance on well-known REDS and GoPro datasets, and bring machine task gain. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion estimation

Unambiguous Imaging for Moving Targets in Maritime Scenarios with Dual Receive Channel Mode of GF-3 Satellite

学校读者我要写书评

暂无评论

Unambiguous Imaging for Moving Targets in Maritime Scenarios...

Asian and Pacific Conference on Synthetic Aperture Radar (APSAR)

作者： Junying Yang Xiaolan Qiu Lihua Zhong Chibiao Ding Lijia Huang Hao Chen Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Institute of Electronics Chinese Academy of Sciences Beijing China Fifth Laboratory Institute of Communication and Tracking Technology Beijing China

ISBN: (数字)9781728129129

ISBN: (纸本)9781728129136

Gaofen-3 (GF-3) is the first Chinese multichannel synthetic aperture radar (SAR) sensor that can operate in the dual receive channel (DRC) mode. Different from the traditional single-channel SAR system, the multichannel SAR system can overcome the inherent limitation to achieve high-resolution and wide-swath (HRWS) at the same time. However, the key challenge it faces is false target suppression. Especially for the moving vessels on the ocean, the existence of false targets will increase false alarm probability and affect the interpretation of SAR images. In this paper, the method of integration of detection, velocity estimation, location, and imaging for moving targets in the HRWS SAR system is proposed as well as applied to get an unambiguous image. The simulation and GF-3 real data experimental results show the validity of the method.

关键词：

Exploration of Image Search Results Quality Assessment

学校读者我要写书评

暂无评论

IEEE Transactions on Big Data 2015年第3期1卷 95-108页

作者： Tian, Xinmei Lu, Yijuan Stender, Nate Yang, Linjun Tao, Dacheng CAS Key Laboratory of Technology Geo-Spatial Information Processing and Application Systems University of Science and Technology of China Hefei230027 China Department of Computer Science Texas State University San MarcosTX78666 United States Department of Computer Science University of Nebraska-Lincoln LincolnNE68588 United States Microsoft Corporation RedmondWA98052-7329 United States Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Image retrieval plays an increasingly important role in our daily lives. There are many factors which affect the quality of image search results, including chosen search algorithms, ranking functions, and indexing features. Applying different settings for these factors generates search result lists with varying levels of quality. However, no setting can always perform optimally for all queries. Therefore, given a set of search result lists generated by different settings, it is crucial to automatically determine which result list is the best in order to present it to users. This paper aims to solve this problem and makes four main innovations. First, a preference learning model is proposed to quantitatively study and formulate the best image search result list identification problem. Second, a set of valuable preference learning related features is proposed by exploring the visual characters of returned images. Third, a query-dependent preference learning model is further designed for building a more precise and query-specific model. Fourth, the proposed approach has been tested on a variety of applications including reranking ability assessment, optimal search engine selection, and synonymous query suggestion. Extensive experimental results on three image search datasets demonstrate the effectiveness and promising potential of the proposed method. © 2015 IEEE.

关键词： Image retrieval

Self-adaptive optical image registration based on optimized analysis of feature points

学校读者我要写书评

暂无评论

Self-adaptive optical image registration based on optimized ...

第二届高分辨率对地观测学术年会

作者： Shi Yue Zhang Daobing Institute of Electronic Chinese Academy of SciencesBeijing 100190China Key Laboratory of Spatial Information Processing and Application System Technology Chinese Academy o

Image registration is an important preprocessing step for image processing such as change detection,image mosaicking in remote sensing,however a crucial problem involved feature-based image registration is how to reliably establish correspondent features between sensed image and reference *** paper presents an automatic self-adaptive image registration method based on analytic energy of control points to improve the traditional ***,an multi-scale segment method based on digital curvelet transform is used to evaluate the quality difference of image pairs,and then self-adaptive parameters of SIFT feature-matching algorithm based on multi-scale grey relation of image quality is proposed to increase the feature points and correspondences;At last,to make sure the accuracy of geometrical transform parameters,a method of correspondences selection based on the distribution and matching energy of control points is *** results demonstrate that the proposed method works well in increasing control points and the correspondences of low quality remote sensing images.

关键词： Image Registration Scale Invariant Feature Transform (SIFT) Self-adaptive keypoint refinement

Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Yang, Xue Sun, Hao Fu, Kun Yang, Jirui Sun, Xian Yan, Menglong Guo, Zhi Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing

Ship detection has been playing a significant role in the field of remote sensing for a long time but it is still full of challenges. The main limitations of traditional ship detection methods usually lie in the complexity of application scenarios, the difficulty of intensive object detection and the redundancy of detection region. In order to solve such problems above, we propose a framework called Rotation Dense Feature Pyramid Networks (R-DFPN) which can effectively detect ship in different scenes including ocean and port. Specifically, we put forward the Dense Feature Pyramid Network (DFPN), which is aimed at solving the problem resulted from the narrow width of the ship. Compared with previous multi-scale detectors such as Feature Pyramid Network (FPN), DFPN builds the high-level semantic feature-maps for all scales by means of dense connections, through which enhances the feature propagation and encourages the feature reuse. Additionally, in the case of ship rotation and dense arrangement, we design a rotation anchor strategy to predict the minimum circumscribed rectangle of the object so as to reduce the redundant detection region and improve the recall. Furthermore, we also propose multi-scale ROI Align for the purpose of maintaining the completeness of semantic and spatial information. Experiments based on remote sensing images from Google Earth for ship detection show that our detection method based on RDFPN representation has a state-of-The-Art performance. Copyright © 2018, The Authors. All rights reserved.

关键词： Remote sensing

Progressive unsupervised person re-identification by tracklet association with spatio-temporal regularization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xie, Qiaokang Zhou, Wengang Qi, Guo-Jun Tian, Qi Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Huawei Cloud EI Product Department Huawei Noah's Ark Laboratory

Existing methods for person re-identification (Re-ID) are mostly based on supervised learning which requires numerous manually labeled samples across all camera views for training. Such a paradigm suffers the scalability issue since in real-world Re-ID application, it is difficult to exhaustively label abundant identities over multiple disjoint camera views. To this end, we propose a progressive deep learning method for unsupervised person Re-ID in the wild by Tracklet Association with Spatio-Temporal Regularization (TASTR). In our approach, we first collect tracklet data within each camera by automatic person detection and tracking. Then, an initial Re-ID model is trained based on within-camera triplet construction for person representation learning. After that, based on the person visual feature and spatio-temporal constraint, we associate cross-camera tracklets to generate cross-camera triplets and update the Re-ID model. Lastly, with the refined Re-ID model, better visual feature of person can be extracted, which further promote the association of cross-camera tracklets. The last two steps are iterated multiple times to progressively upgrade the Re-ID model. To facilitate the study, we have collected a new 4K UHD video dataset named Campus-4K with full frames and full spatio-temporal information. Experimental results show that with the spatio-temporal constraint in the training phase, the proposed approach outperforms the state-of-the-art unsupervised methods by notable margins on DukeMTMC-reID, and achieves competitive performance to fully supervised methods on both DukeMTMC-reID and Campus-4K datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras