检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Tianqi Ye, Xinyi Zhao, Weiyue Pan, Zhiyu Shi, Min Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Transformer. Albeit useful, these techniques introduce heavy computation overheads for MVS. Each pixel densely attends to the whole image. In contrast, we propose to constrain non-local feature augmentation within a pair of lines: each point only attends the corresponding pair of epipolar lines. Our idea takes inspiration from the classic epipolar geometry, which shows that one point with different depth hypotheses will be projected to the epipolar line on the other view. This constraint reduces the 2D search space into the epipolar line in stereo matching. Similarly, this suggests that the matching of MVS is to distinguish a series of points lying on the same line. Inspired by this point-to-line search, we devise a line-to-point non-local augmentation strategy. We first devise an optimized searching algorithm to split the 2D feature maps into epipolar line pairs. Then, an Epipolar Transformer (ET) performs non-local feature augmentation among epipolar line pairs. We incorporate the ET into a learning-based MVS baseline, named ET-MVSNet. ET-MVSNet achieves state-of-the-art reconstruction performance on both the DTU and Tanks-and-Temples benchmark with high efficiency. Code is availab.e at https://***/TQTQliu/ET-MVSNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection Approach

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Du, Zhenbang An, Jiayu Tu, Yunlu Hong, Jiahao Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Open Set Domain Adaptation (OSDA) copes with the distribution and lab.l shifts between the source and target domains simultaneously, performing accurate classification for known classes while identifying unknown class samples in the target domain. Most existing OSDA approaches, depending on the final image feature space of deep models, require manually-tuned thresholds, and may easily misclassify unknown samples as known classes. Mixture-of-Experts (MoE) could be a remedy. Within an MoE, different experts handle distinct input features, producing unique expert routing patterns for various classes in a routing feature space. As a result, unknown class samples may display different expert routing patterns to known classes. This paper proposes Dual-Space Detection, which exploits the inconsistencies between the image feature space and the routing feature space to detect unknown class samples without any threshold. A Graph Router is further introduced to better make use of the spatial information among the image patches. Experiments on three datasets validated the effectiveness and superiority of our approach. © 2020 IEEE.

关键词： Mixture-of-Experts Open Set Domain Adaptation Routing Feature

来源：评论

学校读者我要写书评

暂无评论

3D Cinemagraphy from a Single image

3D Cinemagraphy from a Single Image

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xingyi Li Zhiguo Cao Huiqiang Sun Jianming Zhang Ke Xian Guosheng Lin Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology S-Lab Nanyang Technological University Adobe Research

We present 3D Cinemagraphy, a new technique that mar-ries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emer-gence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthe-size novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Point-Query Quadtree for Crowd Counting, Localization, and More

arXiv

引用

arXiv 2023年

作者： Liu, Chengxin Lu, Hao Cao, Zhiguo Liu, Tongliang Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China The University of Sydney Australia

We show that crowd counting can be viewed as a decomposable point querying process. This formulation enables arbitrary points as input and jointly reasons whether the points are crowd and where they locate. The querying processing, however, raises an underlying problem on the number of necessary querying points. Too few imply underestimation;too many increase computational overhead. To address this dilemma, we introduce a decomposable structure, i.e., the point-query quadtree, and propose a new counting model, termed Point quEry Transformer (PET). PET implements decomposable point querying via data-dependent quadtree splitting, where each querying point could split into four new points when necessary, thus enabling dynamic processing of sparse and dense regions. Such a querying process yields an intuitive, universal modeling of crowd as both the input and output are interpretable and steerable. We demonstrate the applications of PET on a number of crowd-related tasks, including fully-supervised crowd counting and localization, partial annotation learning, and point annotation refinement, and also report state-of-the-art performance. For the first time, we show that a single counting model can address multiple crowd-related tasks across different learning paradigms. Code is availab.e at https://***/cxliu0/PET. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Robust Recognition and Segmentation Algorithm for Retaining Walls in Mining Scenes

A Robust Recognition and Segmentation Algorithm for Retainin...

引用

Chinese Automation Congress (CAC)

作者： Tian Zeng Li Xiao Gang Peng Aoze Wang Zhuo Wang Zhigang Sun Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Intelligence and Automation Huazhong University of Science and Technology Wuhan China

The key for bulldozers to realize automatic operation in mine scenes is whether they can accurately identify and accurately segment the retaining walls, however, because the point cloud dataset of the mine site is too few, resulting in the deep learning-based identification and segmentation algorithm cannot be applied in this scene. At the same time, because of the rugged road surface of the mine scene, the existence of a lot of dust, numerous disturbances, retaining wall features are not obvious and other problems, the algorithms proposed by previous scholars are not perfect enough to solve the problem. We propose a point cloud recognition and segmentation algorithm based on clustering and evaluation function of integrated features. Ours firstly compensates the skew of the point cloud map with RANSAC and down samples the data by gridding the point cloud. Then reduces the influence of dust and truck materials in the scene by normal vector and variance information. Finally, screens out the candidate target class by density clustering, and identifies and segments the retaining wall by integrated feature. Our proposed algorithm is validated in several different real mine scenarios and the results show that ours has high accuracy and strong robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deployment of Heterogeneous Multi-Agent Systems via a PDE Approach

Deployment of Heterogeneous Multi-Agent Systems via a PDE Ap...

引用

Chinese Automation Congress (CAC)

作者： Jingtao Man Zhigang Zeng Qiang Xiao Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China School of Artificial Intelligence and Automation (of Huazhong University of Science and Technology) Wuhan China

Spatial deployment of large-scale heterogeneous multi-agent systems (HMASs) over desired 2D or 3D curves is investigated in this paper. With assumption that HMASs consist of numerous first-order agents (FOAs) and second-order agents (SOAs) that could obtain local information of desired curves and their positions relative to their closest neighbors, the collective dynamics of large-scale HMASs are modeled as heterogeneous partial differential equations (PDEs). In particular, this paper introduces series-dependent topological weights between neighboring agents, which are more versatile and practical than constant topological weights commonly used in previous studies. A novel single-point control scheme is proposed, where an informed agent is situated between the last FOA and first SOA. This operation could not only ensure successful implementation of spatial deployment, but also guarantee well-posedness of the constructed heterogeneous error PDEs. By utilizing inequality techniques, sufficient conditions for exponential convergence of error system are derived. A numerical example is presented to demonstrate effectiveness of the proposed approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-independent event-based consensus of multiple Euler-Lagrange systems with input disturbances

引用

Information Sciences 2024年 675卷

作者： Long, Mingkang An, Qing Su, Housheng School of Artificial Intelligence and Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China Artificial Intelligence School Wuchang University of Technology Wuhan430223 China

This paper investigates leaderless consensus (LLC) and leader-follower consensus (LFC) issues of multiple Euler-Lagrange systems (MELSs) with uncertain system parameters and input disturbances. Firstly, by utilizing event-based control strategy, event-based consensus protocols are proposed to achieve LLC and LFC, respectively. Then, to confirm that no Euler-Lagrange (EL) system will exhibit Zeno behavior under the above event-based consensus protocols, we show that the low bound of event-triggering interval is strictly positive for any time instants. Distinct with the existing related works, the proposed event-triggered consensus protocols only rely on local sampled state, and are irrelevant to the system parameters. Finally, some simulation examples are presented to illustrate the feasibility of the proposed event-based consensus algorithms. © 2024 Elsevier Inc.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

A New Multi-Scale Model for Medium-Term Load Forecasting

A New Multi-Scale Model for Medium-Term Load Forecasting

引用

第35届中国控制与决策会议

作者： Peng Liu Hongliang Fang Jiang-Wen Xiao Yan-Wu Wang Xiao-Kang Liu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology) Ministry of Education

When a large number of distributed power and renewable energy are connected to the smart grid,the volatility and intermittency of renewable energy bring some challenges to the smart ***,accurate medium-term load forecasting is essential because it is conducive to the stability of the power grid and can provide data support for the power generating *** factors affect medium-term load forecasting and the real-time electricity price is a very important factor among *** this paper,a multi-scale model based on LSTM model is proposed to extracts features from 3 different time scales including half-hourly time scale,daily time scale and monthly time *** first,the half-hourly data is processed by a half-hourly data processing layer to extract the half-hourly ***,its output is concatenated with the daily load data and is input into a daily data processing ***,the daily features are concatenated with the monthly load data and they are input into a monthly data processing layer to extract the monthly features and get the final forecasting *** case study results demonstrate that the proposed multi-scale model has better performance than the single-scale models.

关键词： Deep learning medium-term load forecasting LSTM real-time electricity price

来源：评论

学校读者我要写书评

暂无评论

Two-Stage OD Flow Prediction for Emergency in Urban Rail Transit

引用

IEEE Transactions on intelligent Transportation Systems 2024年第1期25卷 920-928页

作者： Zhu, Guangyu Ding, Jiacun Wei, Yun Yi, Yang Xu, Sendren Sheng-Dong Wu, Edmond Q. Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport The Beijing Research Center of Urban Traffic Information Sensing and Service Technologies Beijing100044 China Beijing Mass Transit Railway Operation Corporation Ltd. Beijing100014 China Yangzhou University College of Information Engineering Yangzhou225127 China National Taiwan University of Science and Technology Automation and Control Center The Graduate Institute of Automation and Control Taipei106335 Taiwan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai200240 China

Urban rail transit (URT) is vulnerable to natural disasters and social emergencies including fire, storm and epidemic (such as COVID-19), and real-time origin-destination (OD) flow prediction provides URT operators with important information to ensure the safety of URT system. However, hindered by the high dimensionality of OD flow and the lack of supportive information reflecting the real-time passenger flow changes, study in this area is at the beginning stage. A novel model consisting of two stages is proposed for OD flow prediction. The first stage predicts the inflows of all stations by Long Short-Term Memory (LSTM) in real time, where the dimension is reduced compared with predicting OD flows directly. In the second stage, the notion of separation rate, namely, the proportion of inbound passengers bounding for another station, is estimated. Finally, The OD flow is predicted by multiplying the inflow and separation rate. Experiments based on Hangzhou Metro dataset show the proposed model outperforms the contrast model in weighted mean average error (WMAE) and weighted mean square error (WMSE). Results also suggest that the proposed prediction model performs better on weekdays than on weekends, and with greater accuracy on larger OD flows. © 2000-2011 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Point-Query Quadtree for Crowd Counting, Localization, and More

Point-Query Quadtree for Crowd Counting, Localization, and M...

引用

International Conference on Computer Vision (ICCV)

作者： Chengxin Liu Hao Lu Zhiguo Cao Tongliang Liu Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China The University of Sydney Australia

We show that crowd counting can be viewed as a decomposable point querying process. This formulation enables arbitrary points as input and jointly reasons whether the points are crowd and where they locate. The querying processing, however, raises an underlying problem on the number of necessary querying points. Too few imply underestimation; too many increase computational overhead. To address this dilemma, we introduce a decomposable structure, i.e., the point-query quadtree, and propose a new counting model, termed Point quEry Transformer (PET). PET implements decomposable point querying via data-dependent quadtree splitting, where each querying point could split into four new points when necessary, thus enabling dynamic processing of sparse and dense regions. Such a querying process yields an intuitive, universal modeling of crowd as both the input and output are interpretable and steerable. We demonstrate the applications of PET on a number of crowd-related tasks, including fully-supervised crowd counting and localization, partial annotation learning, and point annotation refinement, and also report state-of-the-art performance. For the first time, we show that a single counting model can address multiple crowd-related tasks across different learning paradigms. Code is availab.e at https://***/cxliu0/PET.

关键词：

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：