检索结果-内蒙古大学图书馆

From multi-view to hollow-3D: Hallucinated hollow-3D R-CNN for 3D object detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Deng, Jiajun Zhou, Wengang Zhang, Yanyong 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 Hefei230026 China The Department of Computer Science University of Science and Technology of China Hefei230026 China

As an emerging data modal with precise distance sensing, LiDAR point clouds have been placed great expectations on 3D scene understanding. However, point clouds are always sparsely distributed in the 3D space, and with unstructured storage, which makes it difficult to represent them for effective 3D object detection. To this end, in this work, we regard point clouds as hollow-3D data and propose a new architecture, namely Hallucinated Hollow-3D R-CNN (H23D R-CNN), to address the problem of 3D object detection. In our approach, we first extract the multi-view features by sequentially projecting the point clouds into the perspective view and the bird-eye view. Then, we hallucinate the 3D representation by a novel bilaterally guided multi-view fusion block. Finally, the 3D objects are detected via a box refinement module with a novel Hierarchical Voxel RoI Pooling operation. The proposed H23D R-CNN provides a new angle to take full advantage of complementary information in the perspective view and the bird-eye view with an efficient framework. We evaluate our approach on the public KITTI Dataset and Waymo Open Dataset. Extensive experiments demonstrate the superiority of our method over the state-of-the-art algorithms with respect to both effectiveness and efficiency. The code will be made available at https://***/djiajunustc/H-23D_R-CNN. Copyright © 2021, The Authors. All rights reserved.

关键词： Object recognition

spatial-temporal water area monitoring of Miyun Reservoir using remote sensing imagery from 1984 to 2020

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Chang Tang, Hairong Ji, Luyan Zhao, Yongchao Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Beijing100190 China

Miyun Reservoir has produced huge benefits in flood control, agricultural irrigation, power generation, aquaculture, tourism, and urban water supply. Accurately water mapping is of great significance to the ecological environment monitoring of the Miyun Reservoir and the management of the South-to-North Water Diversion Project. On the 60th anniversary of the completion of the Miyun Reservoir, we took the Miyun Reservoir as the study area and collected all the Landsat-5 and Landsat-8 remote sensing images from 1984 to 2020 for water mapping. Based on the spectral, topographical and temporal-spatial characteristics of water, we proposed an automated method for long-term researvoir mapping, which can solve the problems caused by cloud, shadow, ice and snow pixels. Moreover, it can also deal with the "same objects with different spectra" and spectral mixed problems. The overall accuracy is as high as 98.2% for the case with no cloud or snow/ice cover. The landscape division index is introduced to analyze the morphological changes of Miyun Reservoir. Based on the mapping results, it is suggested that the water area change of the reservoir can be divided into five periods: "growth period" (1984-1993), "peak period" (1994-1999), "decline period" (2000-2003), "protection period" "(2004-2014), and "recovery period" (2015-2020), during which the east and west areas of the reservoir have experienced the process of "division-combination-division-combination". The largest reservoir area reached 151.6 km2 (1995), and the smallest area was only 57.3 km2 (2004). Moreover, we also find that the largest area in a year occurs from August to September, and the smallest area occurs in May. In addition, we have found that the changes of water area of Miyun Reservoir are closely connected to urban development, government policies and precipitation varitations. The study shows that our method used here are potentially extendable to other reservoirs for long-term area monitoring. © 2021, CC

关键词： Time series analysis

Domain generalization via conditional invariant representations

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Ya Gong, Mingming Tian, Xinmei Liu, Tongliang Tao, Dacheng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems University of Science and Technology of China UBTECH Sydney Artificial Intelligence Institute SIT FEIT University of Sydney Department of Philosophy Carnegie Mellon University Department of Biomedical Informatics University of Pittsburgh

Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: Training data and test data have different distributions, and the training set contains heterogeneous samples from different distributions. Let X denote the features, and Y be the class labels. Existing domain generalization methods address the dataset bias problem by learning a domain-invariant representation h(X) that has the same marginal distribution (h(X)) across multiple source domains. The functional relationship encoded in (Y jX) is usually assumed to be stable across domains such that (Y jh(X)) is also invariant. However, it is unclear whether this assumption holds in practical problems. In this paper, we consider the general situation where both (X) and (Y jX) can change across all domains. We propose to learn a feature representation which has domain-invariant class conditional distributions (h(X)jY ). With the conditional invariant representation, the invariance of the joint distribution (h(X);Y ) can be guaranteed if the class prior (Y ) does not change across training and test domains. Extensive experiments on both synthetic and real data demonstrate the effectiveness of the proposed method. Copyright © 2018, The Authors. All rights reserved.

关键词： Statistical tests

A LINEARLY CONVERGENT METHOD FOR SOLVING HIGH-ORDER PROXIMAL OPERATOR∗

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jingyu, G.A.O. Geng, Xiurui Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences China

Recently, various high-order methods have been developed to solve the convex optimization problem. The auxiliary problem of these methods shares the general form that is the same as the high-order proximal operator proposed by Nesterov. In this paper, we present a linearly convergent method to solve the high-order proximal operator based on the classical proximal operator. In addition, some experiments are performed to demonstrate the performance of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Convex optimization

HIGH-ORDER PROXIMAL POINT ALGORITHM FOR THE MONOTONE VARIATIONAL INEQUALITY PROBLEM AND ITS application

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gao, Jingyu Geng, Xiurui Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences China

The proximal point algorithm (PPA) has been developed to solve the monotone variational inequality problem. It provides a theoretical foundation for some methods, such as the augmented Lagrangian method (ALM) and the alternating direction method of multipliers (ADMM). This paper generalizes the PPA to the pth-order (p ≥ 1) and proves its convergence rate O(1/kp/2). Additionally, the pth-order ALM is proposed based on the pth-order PPA. Some numerical experiments are presented to demonstrate the performance of the pth-order ALM. Copyright © 2023, The Authors. All rights reserved.

关键词： Convex optimization

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

Continual Semantic Segmentation via Mask-Based Class Rebalancing

学校读者我要写书评

暂无评论

Continual Semantic Segmentation via Mask-Based Class Rebalan...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yongjie Guo Siya Chen Hongjian You Key Laboratory of Technology in Geo-Spatial Information Processing and Application System 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

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Continual semantic segmentation (CSS) has risen as a popular field, which aims to acquire new skills constantly without forgetting past knowledge catastrophically. In CSS, we identify that there is a severe imbalance between new classes and old classes, leading to the classifier weight toward new classes. In this paper, we deal with the continual semantic segmentation problem from the class imbalance perspective via mask-based class rebalancing, avoiding the model suffering from catastrophic forgetting. More specifically, the mask-based class rebalancing depends on a mask to combine resampling with reweighting ingenuously, which mitigates the classifier bias toward new classes. Besides, we also propose a frequency knowledge distillation, leveraging multiple frequency components information to maintain the feature representation space for old classes. We demonstrate the effectiveness of our approach with an extensive evaluation of the Pascal-VOC 2012 and ADE20K datasets, significantly outperforming the state-of-the-art method.

关键词： Semantic segmentation Semantics

A Method of Using Multichannel SAR spatial Phase information for Moving Target Positioning

学校读者我要写书评

暂无评论

A Method of Using Multichannel SAR Spatial Phase Information...

IEEE International Conference on Radar

作者： Yini Lv Lihua Zhong Xiaolan Qiu Chibiao Ding Aerospace Information Research Institute Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665468893

Multichannel synthetic aperture radar (SAR) has the ability of high-resolution and wide-swath (HRWS) imaging. Therefore, it has become a vital means of marine surveillance. Moreover, the target positioning using SAR is essential in ship monitoring, and it is mainly concentrated on the image domain at present. This paper proposes a novel method of positioning the target using the spatial phase information of SAR echo without imaging. The multichannel SAR antenna can be regarded as an array composed of multiple elements, and based on the array signal processing theory, the target cone angle at the imaging moment can be obtained. Then, according to the range-Doppler equation and the geometric model of the earth, the target coordinates can be calculated with the cone angle known. Finally, the results of the simulation experiment illustrate the effectiveness of the proposed method.

关键词： Earth Array signal processing Surveillance geometric modeling Imaging Signal processing algorithms Radar imaging

AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yonghui Zhou, Wengang Feng, Hao 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 Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

Over the past few years, the advancement of Multimodal Large Language Models (MLLMs) has captured the wide interest of researchers, leading to numerous innovations to enhance MLLMs’ comprehension. In this paper, we present AdaptVision, a multimodal large language model specifically designed to dynamically process input images at varying resolutions. We hypothesize that the requisite number of visual tokens for the model is contingent upon both the resolution and content of the input image. Generally, natural images with a lower information density can be effectively interpreted by the model using fewer visual tokens at reduced resolutions. In contrast, images containing textual content, such as documents with rich text, necessitate a higher number of visual tokens for accurate text interpretation due to their higher information density. Building on this insight, we devise a dynamic image partitioning module that adjusts the number of visual tokens according to the size and aspect ratio of images. This method mitigates distortion effects that arise from resizing images to a uniform resolution and dynamically optimizing the visual tokens input to the LLMs. Our model is capable of processing images with resolutions up to 1008 × 1008. Extensive experiments across various datasets demonstrate that our method achieves impressive performance in handling vision-language tasks in both natural and text-related scenes. The source code and dataset are now publicly available at https://***/harrytea/AdaptVision. Copyright © 2024, The Authors. All rights reserved.

关键词： Modeling languages