检索结果-内蒙古大学图书馆

UNSUPERVISED STEREO MATCHING NETWORK FOR VHR REMOTE SENSING IMAGES BASED ON ERROR PREDICTION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Liting Xiang, Yuming Wang, Feng You, Hongjian Aerospace Information Research Institute Chinese Academy of Sciences 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 Beijing101408 China

Stereo matching in remote sensing has recently garnered increased attention, primarily focusing on supervised learning. However, datasets with ground truth generated by expensive airbone Lidar exhibit limited quantity and diversity, constraining the effectiveness of supervised networks. In contrast, unsupervised learning methods can leverage the increasing availability of very-high-resolution (VHR) remote sensing images, offering considerable potential in the realm of stereo matching. Motivated by this intuition, we propose a novel unsupervised stereo matching network for VHR remote sensing images. A light-weight module to bridge confidence with predicted error is introduced to refine the core model. Robust unsupervised losses are formulated to enhance network convergence. The experimental results on US3D and WHU-Stereo datasets demonstrate that the proposed network achieves superior accuracy compared to other unsupervised networks and exhibits better generalization capabilities than supervised models. Our code will be available at https://***/Elenairene/CBEM. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

Recurrent Generic Contour-based Instance Segmentation with Progressive Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Hao Zhou, keyi Zhou, Wengang Yin, Yufei Deng, Jiajun Sun, 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 Zhangjiang Laboratory Shanghai China University of Adelaide Australian Institute for Machine Learning Australia

Contour-based instance segmentation has been actively studied, thanks to its flexibility and elegance in processing visual objects within complex backgrounds. In this work, we propose a novel deep network architecture, i.e., PolySnake, for generic contour-based instance segmentation. Motivated by the classic Snake algorithm, the proposed PolySnake achieves superior and robust segmentation performance with an iterative and progressive contour refinement strategy. Technically, PolySnake introduces a recurrent update operator to estimate the object contour iteratively. It maintains a single estimate of the contour that is progressively deformed toward the object boundary. At each iteration, PolySnake builds a semantic-rich representation for the current contour and feeds it to the recurrent operator for further contour adjustment. Through the iterative refinements, the contour progressively converges to a stable status that tightly encloses the object instance. Beyond the scope of general instance segmentation, extensive experiments are conducted to validate the effectiveness and generalizability of our PolySnake in two additional specific task scenarios, including scene text detection and lane detection. The results demonstrate that the proposed PolySnake outperforms the existing advanced methods on several multiple prevalent benchmarks across the three tasks. The codes and pre-trained models are available at https://***/fh2019ustc/PolySnake Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

Deep Unrestricted Document Image Rectification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Hao 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 Zhangjiang Laboratory Shanghai China The University of Adelaide Australian Institute for Machine Learning Australia

In recent years, tremendous efforts have been made on document image rectification, but existing advanced algorithms are limited to processing restricted document images, i.e., the input images must incorporate a complete document. Once the captured image merely involves a local text region, its rectification quality is degraded and unsatisfactory. Our previously proposed DocTr, a transformer-assisted network for document image rectification, also suffers from this limitation. In this work, we present DocTr++, a novel unified framework for document image rectification, without any restrictions on the input distorted images. Our major technical improvements can be concluded in three aspects. Firstly, we upgrade the original architecture by adopting a hierarchical encoder-decoder structure for multi-scale representation extraction and parsing. Secondly, we reformulate the pixel-wise mapping relationship between the unrestricted distorted document images and the distortion-free counterparts. The obtained data is used to train our DocTr++ for unrestricted document image rectification. Thirdly, we contribute a real-world test set and metrics applicable for evaluating the rectification quality. To our best knowledge, this is the first learning-based method for the rectification of unrestricted document images. Extensive experiments are conducted, and the results demonstrate the effectiveness and superiority of our method. We hope our DocTr++ will serve as a strong baseline for generic document image rectification, prompting the further advancement and application of learning-based algorithms. The source code and the proposed dataset are publicly available at https://***/fh2019ustc/DocTr-Plus. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Deep amended COPERT model for regional vehicle emission prediction

学校读者我要写书评

暂无评论

Science China(information Sciences) 2021年第3期64卷 238-240页

作者： Zhenyi XU Yu KANG Yang CAO Zerui LI Department of Automation University of Science and Technology of China Key Laboratory of Technology in Geo Spatial Information Processing and Application System Chinese Academy of Sciences

Dear editor,The existing methods for regional vehicle emission prediction can be roughly categorized into the classes of classical dispersion models and satellite remote sensing *** plume models, operational street ca...

关键词：

Rethinking the key Factors for the Generalization of Remote Sensing Stereo Matching Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Liting Wang, Feng Zhang, Wenyi Li, Peifeng You, Hongjian Xiang, Yuming Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China The Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing100190 China Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China

Stereo matching, a critical step of 3D reconstruction, has fully shifted towards deep learning due to its strong feature representation of remote sensing images. However, ground truth for stereo matching task relies on expensive airborne LiDAR data, thus making it difficult to obtain enough samples for supervised learning. To improve the generalization ability of stereo matching networks on cross-domain data from different sensors and scenarios, in this paper, we dedicate to study key training factors from three perspectives. (1) For the selection of training dataset, it is important to select data with similar regional target distribution as the test set instead of utilizing data from the same sensor. (2) For model structure, cascaded structure that flexibly adapts to different sizes of features is preferred. (3) For training manner, unsupervised methods generalize better than supervised methods, and we design an unsupervised early-stop strategy to help retain the best model with pre-trained weights as the basis. Extensive experiments are conducted to support the previous findings, on the basis of which we present an unsupervised stereo matching network with good generalization performance. We release the source code and the datasets at https://***/Elenairene/RKF_RSSM to reproduce the results and encourage future work. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

Multi-aspect Tomographic SAR Imaging Approach via Distributed Compressed Sensing and Joint Sparsity

学校读者我要写书评

暂无评论

Multi-aspect Tomographic SAR Imaging Approach via Distribute...

2021 CIE International Conference on Radar, Radar 2021

作者： Du, Bang Zhang, Zhe Qiu, Xiaolan Lei, Bin Ding, Chibiao Key Laboratory of Technology in Geo-spatial Information Processing and Application System Beijing China Beijing China University of Chinese Academy of Sciences Beijing China Aerospace Information Research Institute Chinese Academy of Sciences Suzhou China

ISBN: (纸本)9781665498142

Synthetic aperture radar (SAR) tomography (TomoSAR) is a novel technique that enables three-dimensional (3-D) imaging and plays an important role in urban remote sensing by utilizing multiple observations of the same target scene from various baselines. Canonical TomoSAR observations are from a single aspect, which has been well studies already. However, modern SAR sensors such as Unmanned Aerial Vehicle (UAV) allow us to achieve multi-aspect TomoSAR data of the same target scene. This paper proposes a novel framework named 'Multi-aspect TomoSAR,' which takes advantage of rich TomoSAR data from multiple observation aspects. We derive the multi-aspect TomoSAR signal model using distributed compressed sensing (DCS) and adopt a simultaneous sparse approximation algorithm named SOMP to solve the joint sparsity model. Numerical results on synthetic simulated data show that the multi-aspect estimation can provide more accurate estimation, yield a promising perspective. Experimental results on real airborne data will be reported in the journal version of this work later. © 2021 IEEE.

关键词： Distributed compressed sensing Joint sparsity model Multi-aspect TomoSAR

Pattern Analysis and Placement Optimization of the Four-horn Monopulse for Terahertz Communication

学校读者我要写书评

暂无评论

Pattern Analysis and Placement Optimization of the Four-horn...

2023 Cross Strait Radio Science and Wireless technology Conference, CSRSWTC 2023

作者： Lu, Yong-Han Zhu, Zhong-Bo Ma, Jing Shi, Bin Zhang, Yu-Ting Peng, Lin Guilin University of Electronic Technology Key Laboratory of Microwave and Optical Wave Application Technology Guangxi Guilin541004 China National Key Laboratory of Science and Technology on Space Microwave Xi'an710100 China Beijing Simulation Center Science and Technology on Special System Simulation Laboratory Beijing100854 China School of Optoelectronic Engineering Guangxi Key Laboratory of Optoelectronic Information Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9798350358971

The mobile node communication in terahertz monopulse system requires narrow beam to align with the mobile target precisely. In this paper, the radiation pattern of four-horn monopulse antenna is analyzed by use of the geometric optics (GO) and aperture field integration method (AFIM), and an efficient placement optimization to reduce the beamwidth of four-horn monopulse is presented. The optimization combines the genetic algorithm (GA) with GO-AFIM. The GA is employed to seek the optimal positions of the four horns, and the GO and AFIM are introduced into the fitness function of GA to evaluate the individual fitness. The optimization result has narrowed the beamwidth and enhanced gain of radiation pattern. Compared with the simulation in full wave software, the proposed method costs less time in pattern analysis and performs more efficiently in placement optimization. © 2023 IEEE.

关键词： aperture field integration method (AFIM) geometric optics (GO) placement optimization terahertz monopulse

SPHR-SAR-Net: Superpixel High-resolution SAR Imaging Network Based on Nonlocal Total Variation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Guoru Xu, Zhongqiu Fan, Yizhe Zhang, Zhe Qiu, Xiaolan Zhang, Bingchen Fu, Kun Wu, Yirong The Key Laboratory of Technology in Geo-spatial Information Processing Application System Chinese Academy of Sciences Beijing China Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology Suzhou Aerospace Information Research Institute Jiangsu Suzhou China Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China

High-resolution is a key trend in the development of synthetic aperture radar (SAR), which enables the capture of fine details and accurate representation of backscattering properties. However, traditional high-resolution SAR imaging algorithms face several challenges. Firstly, these algorithms tend to focus on local information, neglecting non-local information between different pixel patches. Secondly, speckle is more pronounced and difficult to filter out in high-resolution SAR images. Thirdly, the process of high-resolution SAR imaging generally involves high time and computational complexity, making real-time imaging difficult to achieve. To address these issues, we propose a Superpixel High-Resolution SAR Imaging Network (SPHR-SAR-Net) for rapid despeckling in high-resolution SAR mode. Based on the concept of superpixel techniques, we initially combine nonconvex and non-local total variation as compound regularization. This approach more effectively despeckles and manages the relationship between pixels while reducing bias effects caused by convex constraints. Subsequently, we solve the compound regularization model using the Alternating Direction Method of Multipliers (ADMM) algorithm and unfold it into a Deep Unfolded Network (DUN). The network’s parameters are adaptively learned in a data-driven manner, and the learned network significantly increases imaging speed. Additionally, the Deep Unfolded Network is compatible with high-resolution imaging modes such as spotlight, staring spotlight, and sliding spotlight. In this paper, we demonstrate the superiority of SPHR-SAR-Net through experiments in both simulated and real SAR scenarios. The results indicate that SPHR-SAR-Net can rapidly perform high-resolution SAR imaging from raw echo data, producing accurate imaging results. Copyright © 2023, The Authors. All rights reserved.

关键词： Synthetic aperture radar

A Method for Analyzing Strong Scattering in SAR Images Based on a Differentiable Simulator

学校读者我要写书评

暂无评论

A Method for Analyzing Strong Scattering in SAR Images Based...

IEEE International Symposium on geoscience and Remote Sensing (IGARSS)

作者： Zinan Liu Shengren Niu Xiaolan Qiu Lingxiao Peng Chibiao Ding Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems 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 Key Laboratory of Microwave Imaging Processing and Application Technology Suzhou Aerospace Information Research Institute Chinese Academy of Sciences Suzhou China The National Key Laboratory of Microwave Imaging Technology Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Synthetic Aperture Radar (SAR) is extensively employed in earth remote sensing, including both civilian and military sectors. Currently, establishing the correspondence between strong scattering regions in SAR images and the 3D geometry of the target has become a research hotspot. Traditional methods based on scattering center modeling overly rely on prior knowledge and manual annotation. However, neural network-based approaches often lack the constraints of SAR imaging principles when performing feature extraction. In this paper, we propose a method for analyzing strong scattering in SAR images based on a differentiable simulator to visualize the correspondence between strong scattering in SAR images and the 3D geometry of the target. Specifically, the differentiable simulator accumulates the scattering intensity in the scattering simulation stage to generate simulated SAR images at multi-pose. By computing the loss with the SAR image in the dataset (ground truth), the differentiable simulator can provide a direct mapping from the strong scattering in SAR images to the target's 3D structures. The effectiveness of the method is validated on a dataset of simulated SAR images based on the MSTAR. From the result we obtained, the correspondence between the 3D structures of the target model and the strong scattering in the image can be intuitively and clearly determined.

关键词： geometry Training Visualization Solid modeling Three-dimensional displays Scattering Radar polarimetry