检索结果-内蒙古大学图书馆

Accelerating Globally Optimal consensus maximization in Geometric Vision

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第6期46卷 4280-4297页

作者： Zhang, Xinyue Peng, Liangzu Xu, Wanting Kneip, Laurent ShanghaiTech Univ Mobile Percept Lab Shanghai 201210 Peoples R China Shanghai Engn Res Ctr Intelligent Vis & Imaging Mobile Percept Lab Shanghai 201210 Peoples R China

Branch-and-bound-based consensus maximization stands out due to its important ability of retrieving the globally optimal solution to outlier-affected geometric problems. However, while the discovery of such solutions caries high scientific value, its application in practical scenarios is often prohibited by its computational complexity growing exponentially as a function of the dimensionality of the problem at hand. In this work, we convey a novel, general technique that allows us to branch over an n-1 dimensional space for an n-dimensional problem. The remaining degree of freedom can be solved globally optimally within each bound calculation by applying the efficient interval stabbing technique. While each individual bound derivation is harder to compute owing to the additional need for solving a sorting problem, the reduced number of intervals and tighter bounds in practice lead to a significant reduction in the overall number of required iterations. Besides an abstract introduction of the approach, we present applications to four fundamental geometric computer vision problems: camera resectioning, relative camera pose estimation, point set registration, and rotation and focal length estimation. Through our exhaustive tests, we demonstrate significant speed-up factors at times exceeding two orders of magnitude, thereby increasing the viability of globally optimal consensus maximizers in online application scenarios.

关键词： Cameras Three-dimensional displays Computer vision Fitting Computational modeling Pose estimation Optimization Branch and bound consensus maximization geometric vision interval stabbing

来源：评论

学校读者我要写书评

暂无评论

Practical globally optimal consensus maximization by Branch-and-bound based on interval arithmetic

引用

PATTERN RECOGNITION 2021年 115卷 107897-107897页

作者： Wang, Yiru Liu, Yinlong Li, Xuechen Wang, Chen Wang, Manning Song, Zhijian Fudan Univ Digital Med Res Ctr Sch Basic Med Sci Shanghai 200032 Peoples R China Shanghai Key Lab Med Image Comp & Comp Assisted I Shanghai 200032 Peoples R China Tech Univ Munich Dept Informat D-85748 Garching Germany

consensus maximization is widely used in robust model fitting, and it is usually solved by RANSAC-type methods in practice. However, these methods cannot guarantee global optimality and sometimes return the wrong solutions. A series of Branch-and-bound (BnB) based globally optimal methods have been proposed, most of which involve deriving a complex bound. Interval arithmetic was utilized to derive simple bounds for BnB in solving geometric matching problems in 2003. However, this idea was somewhat forgotten in the community because it seems natural that the simple interval arithmetic based bounds might be worse than those elaborate bounds. Recently, some new globally optimal algorithms without using BnB were developed for consensus maximization, but they can only work with a small number of data points and low outlier ratios. In this work, we draw the idea of simple bounds by interval arithmetic back on the map and demonstrate its practicability by making substantial extensions. Concretely, we give detailed derivation of solving robust model fitting problems with both linear and quasi-convex residuals and propose practical methods to use them under Unit-Norm constraint and in a high-dimensional problem. Extensive experiments show that the proposed method can handle practical problems with large number of data points and high outlier ratios. It outperforms state-of-the-art global, RANSAC-type, and deterministic methods in terms of both accuracy and efficiency in low-dimensional problems. The source code is publicly available. 2 (c) 2021 Elsevier Ltd. All rights reserved.

关键词： consensus maximization Globally optimization Robust model fitting Branch-and-bound Interval arithmetic

来源：评论

学校读者我要写书评

暂无评论

Deterministic consensus maximization with Biconvex Programming 15th

Deterministic Consensus Maximization with Biconvex Programmi...

引用

15th European Conference on Computer Vision (ECCV)

作者： Cai, Zhipeng Chin, Tat-Jun Le, Huu Suter, David Univ Adelaide Sch Comp Sci Adelaide SA Australia Queensland Univ Technol Sch Elect Engn & Comp Sci Brisbane Qld Australia Edith Cowan Univ Sch Comp & Secur Joondalup Australia

ISBN: (纸本)9783030012588;9783030012571

consensus maximization is one of the most widely used robust fitting paradigms in computer vision, and the development of algorithms for consensus maximization is an active research topic. In this paper, we propose an efficient deterministic optimization algorithm for consensus maximization. Given an initial solution, our method conducts a deterministic search that forcibly increases the consensus of the initial solution. We show how each iteration of the update can be formulated as an instance of biconvex programming, which we solve efficiently using a novel biconvex optimization algorithm. In contrast to our algorithm, previous consensus improvement techniques rely on random sampling or relaxations of the objective function, which reduce their ability to significantly improve the initial consensus. In fact, on challenging instances, the previous techniques may even return a worse off solution. Comprehensive experiments show that our algorithm can consistently and greatly improve the quality of the initial solution, without substantial cost. (Matlab demo program is available in the supplementary material)

关键词： Robust fitting consensus maximization Biconvex programming

来源：评论

学校读者我要写书评

暂无评论

Transformation Decoupling Strategy Based on Screw Theory for Deterministic Point Cloud Registration With Gravity Prior

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第12期46卷 10515-10532页

作者： Li, Xinyi Ma, Zijian Liu, Yinlong Zimmer, Walter Cao, Hu Zhang, Feihu Knoll, Alois Tech Univ Munich TUM Sch Computat Informat & Technol Chair Robot Artificial Intelligence & Real Time S D-85748 Munich Germany Tech Univ Munich TUM Sch Engn & Design D-85748 Munich Germany Univ Macau State Key Lab Internet Things Smart City SKL IOTS Macau 999078 Peoples R China Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Peoples R China

Point cloud registration is challenging in the presence of heavy outlier correspondences. This paper focuses on addressing the robust correspondence-based registration problem with gravity prior that often arises in practice. The gravity directions are typically obtained by inertial measurement units (IMUs) and can reduce the degree of freedom (DOF) of rotation from 3 to 1. We propose a novel transformation decoupling strategy by leveraging the screw theory. This strategy decomposes the original 4-DOF problem into three sub-problems with 1-DOF, 2-DOF, and 1-DOF, respectively, enhancing computation efficiency. Specifically, the first 1-DOF represents the translation along the rotation axis, and we propose an interval stabbing-based method to solve it. The second 2-DOF represents the pole which is an auxiliary variable in screw theory, and we utilize a branch-and-bound method to solve it. The last 1-DOF represents the rotation angle, and we propose a global voting method for its estimation. The proposed method solves three consensus maximization sub-problems sequentially, leading to efficient and deterministic registration. In particular, it can even handle the correspondence-free registration problem due to its significant robustness. Extensive experiments on both synthetic and real-world datasets demonstrate that our method is more efficient and robust than state-of-the-art methods, even when dealing with outlier rates exceeding 99%.

关键词： Point cloud compression Gravity Three-dimensional displays Fasteners 2-DOF Pose estimation Optimization Branch-and-bound consensus maximization gravity direction interval stabbing rigid point cloud registration robust estimation screw theory

来源：评论

学校读者我要写书评

暂无评论

Fast and deterministic (3+1)DOF point set registration with gravity prior

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2023年第1期199卷 118-132页

作者： Li, Xinyi Liu, Yinlong Xia, Yan Lakshminarasimhan, Venkatnarayanan Cao, Hu Zhang, Feihu Stilla, Uwe Knoll, Alois Tech Univ Munich Chair Robot Artificial Intelligence & Realtime Sys TUM Sch Computat Informat & Technol D-85748 Munich Germany Univ Macau State Key Lab Internet Things Smart City SKL IOTSC Zhuhai 999078 Peoples R China Tech Univ Munich TUM Sch Engn & Design Photogrammetry & Remote Sensing D-80333 Munich Germany Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Peoples R China

Point set registration is the technology used to estimate the spatial transformation between two LiDAR scans, which is challenging in the presence of outlier correspondences and noise. Our focus is on 4 degrees of freedom (DOF) point set registration, in which 1DOF rotation and 3DOF translation need to be estimated. It is commonly found in practical scenarios, such as arbitrarily mobile robots equipped with an inertial measurement unit (IMU), terrestrial LiDAR scanners, or planar moving vehicles in urban environments. Recently, many solutions have leveraged branch and bound (BnB) in global and deterministic approaches to solve the registration problem with performance guarantees. However, BnB-based methods are usually time-consuming since their convergence speed is exponential to the dimensionality of the solution domain, and existing methods estimate these 4DOF simultaneously. Our key idea is to speed up BnB-based methods by decoupling the joint pose into separate translation and rotation with the aid of known gravity directions. This effectively reduces the search domain to 3DOF+1DOF, thereby enhancing algorithm efficiency. Specifically, we propose a novel BnB-based consensus maximization method for a fast 3DOF translation search and derive the specific lower and upper bound functions. We then propose an efficient global voting method for estimating the rotation with 1DOF. To demonstrate the superiority of our proposed method, we conduct extensive experiments on both synthetic and real-world datasets. The experimental results show that (1) our proposed method is more robust against outliers and noise than several existing methods and far faster than the existing BnB-based 4DOF method by almost an order of magnitude, (2) our proposed method is robust against the biases in gravity directions, such that the general error of the IMU is acceptable, and (3) thanks to its significant robustness, our proposed method can solve the challenging problem of simultaneous pose a

关键词： Point set registration Gravity direction consensus maximization Branch and bound Correspondence-based registration Simultaneous pose and correspondence registration

来源：评论

学校读者我要写书评

暂无评论

VODRAC: Efficient and robust correspondence-based point cloud registration with extreme outlier ratios

引用

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2023年第1期35卷 38-55页

作者： Hu, Enwen Sun, Lei Beijing Univ Posts & Telecommun Sch Artificial Intelligence Beijing Peoples R China East China Univ Sci & Technol Sch Mech & Power Engn Shanghai Peoples R China

Point set registration (PSR) from correspondences is a basic problem in the area of computer vision, robotics and remote sensing. Nevertheless, because of the limited accuracy of current correspondence building and feature matching technologies, PSR is frequently afflicted by the problem of outliers. In this work, we put forward VODRAC (VOting-based Double-point RAndom sampling with Compatibility weighting), a fast, highly robust and practically effective solution for the PSR problem as well as its real-world applications. To realize this, our first contribution is to integrate the scale-invariant constraint with a double-point random sampling framework to achieve the rapid seeking of inlier candidates and the rough rejection of outliers in the meantime. The second contribution is that we introduce the concept of weight matrix for PSR which is to use the robust loss function for weight computation between pairwise correspondences and also propose a time-efficient way to embed the construction of this matrix into the operation of the algorithm without requiring additional computational time. Moreover, we employ the correspondence voting technique to accelerate the consensus maximization (convergence) of the algorithm, as our third contribution. Through comprehensive experiments over multiple actual datasets, we demonstrate that VODRAC is fast, accurate, and highly robust against up to 99% of outliers (e.g. solving PSR within 2 s when there exist 99% outliers among 1000 correspondences), outperforming existing state-of-the-art (SOTA) robust algorithms.& COPY;2022 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Point set registration Robust estimation consensus maximization Object localization Scan matching

来源：评论

学校读者我要写书评

暂无评论

Multiway Point Cloud Mosaicking with Diffusion and Global Optimization

Multiway Point Cloud Mosaicking with Diffusion and Global Op...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jin, Shengze Armeni, Iro Pollefeys, Marc Barath, Daniel Swiss Fed Inst Technol Dept Comp Sci Zurich Switzerland Stanford Univ Dept Civil & Environm Engn Stanford CA USA Microsoft Mixed Real & AI Lab Zurich Switzerland

ISBN: (纸本)9798350353006

We introduce a novel framework for multiway point cloud mosaicking (named Wednesday), designed to co-align sets of partially overlapping point clouds - typically obtained from 3D scanners or moving RGB-D cameras - into a unified coordinate system. At the core of our approach is ODIN, a learned pairwise registration algorithm that iteratively identifies overlaps and refines attention scores, employing a diffusion-based process for denoising pair-wise correlation matrices to enhance matching accuracy. Further steps include constructing a pose graph from all point clouds, performing rotation averaging, a novel robust algorithm for re-estimating translations optimally in terms of consensus maximization and translation optimization. Finally, the point cloud rotations and positions are optimized jointly by a diffusion-based approach. Tested on four diverse, large-scale datasets, our method achieves state-of-the-art pairwise and multiway registration results by a large margin on all benchmarks. Our code and models are available at https://***/jinsz/Multiway-Point-CloudMosaicking-with-Diffusion-and-Global-Optimization.

关键词： attention learning consensus maximization diffusion model global optimization multiway point cloud registration pairwise point cloud registration point cloud mosaicking point cloud registration rotation averaging translation averaging

来源：评论

学校读者我要写书评

暂无评论

Practical, Fast and Robust Point Cloud Registration for Scene Stitching and Object Localization

引用

IEEE ACCESS 2022年 10卷 3962-3978页

作者： Sun, Lei East China Univ Sci & Technol Sch Mech & Power Engn Shanghai 200237 Peoples R China Shanghai FOCS Anal Instrument Co Ltd Prod Res & Dev Dept Shanghai 201802 Peoples R China

3D point cloud registration ranks among the most fundamental problems in remote sensing, photogrammetry, robotics and geometric computer vision. Due to the limited accuracy of 3D feature matching techniques, outliers may exist, sometimes even in very large numbers, among the correspondences. Since existing robust solvers may encounter high computational cost or restricted robustness, we propose a novel, fast and highly robust solution, named VOCRA (VOting with Cost function and Rotating Averaging), for the point cloud registration problem with extreme outlier rates. Our first contribution is to employ the Tukey's Biweight robust cost to introduce a new voting and correspondence sorting technique, which proves to be rather effective in distinguishing true inliers from outliers even with extreme (99%) outlier rates. Our second contribution consists in designing a time-efficient consensus maximization paradigm based on robust rotation averaging, serving to seek inlier candidates among the correspondences. Finally, we apply Graduated Non-Convexity with Tukey's Biweight (GNC-TB) to estimate the correct transformation with the inlier candidates obtained, which is then used to find the complete inlier set. Both standard benchmarking and realistic experiments with application to two real-data problems are conducted, and we show that our solver VOCRA is robust against over 99% outliers (exceeding traditional GNC by nearly 10% and RANSAC by nearly 4%) and more time-efficient than the state-of-the-art competitors.

关键词： Point cloud compression Three-dimensional displays Estimation Sun Runtime Robustness Costs Point cloud registration robust estimation graduated non-convexity consensus maximization scene stitching object localization

来源：评论

学校读者我要写书评

暂无评论

Using Graph-Based Ensemble Learning to Classify Imbalanced Data 3

Using Graph-Based Ensemble Learning to Classify Imbalanced D...

引用

3rd IEEE International Conference on Cybernetics (CYBCONF)

作者： Qin, Anyong Shang, Zhaowei Tian, Jinyu Zhang, Taiping Wang, Yulong Tang, Yuan Yan Chongqing Univ Coll Comp Sci Chongqing 400030 Peoples R China Chongqing Univ Coll Math & Stat Chongqing 400030 Peoples R China Chengdu Univ Coll Informat Sci & Engn Chengdu 610100 Sichuan Peoples R China Univ Macau Fac Sci & Technol Macau 999078 Peoples R China

ISBN: (纸本)9781538622018

The class imbalance problems have attracted considerable attention from researchers of different fields. Ensemble learning has emerged as a powerful approach to address the imbalanced data and improved accuracy and robustness over the single model. In this paper, we present a novel ensemble method based on a bipartite graph (GraphEL) by maximizing the consensus among the multiple binary models. In this bipartite graph, we take into account the probability offered by the multiple classifiers and the average distance provided by the original data, which appear in the graph in the form of weights. Experimental results on 22 imbalanced data sets demonstrate the benefits of the proposed method over the conventional imbalance data handing methods.

关键词： Imbalanced data Ensemble learning consensus maximization

来源：评论

学校读者我要写书评

暂无评论

Researcher Homepage Classification using Unlabeled Data 13

Researcher Homepage Classification using Unlabeled Data

引用

International Conference on World Wide Web

作者： Sujatha Das G. Cornelia Caragea Prasenjit Mitra C. Lee Giles Computer Science and Engineering The Pennsylvania State University University Park PA-16803 Computer Science and Engineering University of North Texas Denton TX-76203 Computer Science and Engineering Information Sciences and TechnologyThe Pennsylvania State University University Park PA-16803

ISBN: (纸本)9781450322942

A classifier that determines if a webpage is relevant to a specified set of topics comprises a key component for focused crawling. Can a classifier that is tuned to perform well on training datasets continue to filter out irrelevant pages in the face of changed content on the Web? We investigate this question in the context of researcher homepage crawling. We show experimentally that classifiers trained on existing datasets for homepage identification underperform while classifying "irrelevant" pages on current-day academic websites. As an alternative to obtaining datasets to retrain the classifier for the new content, we propose to use effectively unlimited amounts of unlabeled data readily available from these websites in a co-training scenario. To this end, we design novel URL-based features and use them in conjunction with content-based features as complementary views of the data to obtain remarkable improvements in accurately identifying homepages from the current-day university websites. In addition, we propose a novel technique for "learning a conforming pair of classifiers" using mini-batch gradient descent. Our algorithm seeks to minimize a loss (objective) function quantifying the difference in predictions from the two views afforded by co-training. We demonstrate that tuning the classifiers so that they make "similar" predictions on unlabeled data strongly corresponds to the effect achieved by co-training algorithms. We argue that this loss formulation provides insight into understanding the co-training process and can be used even in absence of a validation set.

关键词： co-training consensus maximization gradient descent

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：