检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yu, Jingwen Ye, Hanjing Jiao, Jianhao Tan, Ping Zhang, Hong The Hong Kong University of Science and Technology Hong Kong Hong Kong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Computer Science University College London London United Kingdom

Visual loop closure detection is an important module in visual simultaneous localization and mapping (SLAM), which associates current camera observation with previously visited places. Loop closures correct drifts in trajectory estimation to build a globally consistent map. However, a false loop closure can be fatal, so verification is required as an additional step to ensure robustness by rejecting the false positive loops. Geometric verification has been a well-acknowledged solution that leverages spatial clues provided by local feature matching to find true positives. Existing feature matching methods focus on homography and pose estimation in long-term visual localization, lacking references for geometric verification. To fill the gap, this paper proposes a unified benchmark targeting geometric verification of loop closure detection under long-term conditional variations. Furthermore, we evaluate six representative local feature matching methods (handcrafted and learning-based) under the benchmark, with in-depth analysis for limitations and future directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Controllable Segmentation-Based Text-Guided Style Editing

arXiv

引用

arXiv 2025年

作者： Li, Jingwen Chandrasekar, Aravind Rocha, Mariana Li, Chao Chen, Yuqing Department of Computer Science Fudan University China School of AI and Robotics AuroraTech Labs United States Vision Intelligence Group Federal University of Rio de Janeiro Brazil Dept. of Computer Science Eastern Asia Institute of Technology Beijing China

We present a novel approach for controllable, region-specific style editing driven by textual prompts. Building upon the state-space style alignment framework introduced by StyleMamba, our method integrates a semantic segmentation model into the style transfer pipeline. This allows users to selectively apply text-driven style changes to specific segments (e.g., "turn the building into a cyberpunk tower") while leaving other regions (e.g., "people" or "trees") unchanged. By incorporating region-wise condition vectors and a region-specific directional loss, our method achieves high-fidelity transformations that respect both semantic boundaries and user-driven style descriptions. Extensive experiments demonstrate that our approach can flexibly handle complex scene stylizations in real-world scenarios, improving control and quality over purely global style transfer methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Tile-Based Multi-Scale Detection: Designing a Simple and Effective Pipeline

Tile-Based Multi-Scale Detection: Designing a Simple and Eff...

引用

International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)

作者： Alexander Chernikov Dmitrii Stepanov Aleksandr Bakhshiev Higher School of Automation and Robotics Peter the Great St. Petersburg Polytechnic University St. Petersburg Russia R&D Department Computer Vision Systems LLC St. Petersburg Russia

ISBN: (数字)9798331512194

ISBN: (纸本)9798331512200

Object detection in large images poses significant challenges, especially when objects vary in size and appear at different scales. This is particularly relevant in remote sensing, defect detection, and map analysis, where high-resolution images contain objects of interest ranging from small, densely packed instances to large, sparse structures. In this work, we explore the design of a simple yet effective tile-based multi-scale object detection pipeline. The proposed approach divides images into smaller tiles for each chosen scale and then aggregate outputs to get the final results. To maintain efficiency, we employ one lightweight detection model and investigate various fusion techniques, including object stitching in overlapping regions, non-maximum suppression (NMS), soft NMS, and score voting. Additionally, we propose hybrid NMS, new aggregation method, that was developed to eliminate the disadvantages of previous methods. Experimental evaluation on DOTAv1 dataset demonstrates that our approach enhances detection accuracy without significantly increasing computational cost. The findings highlight the potential of tile-based multi-scale processing for applications requiring precise and robust object localization in large-scale images. Source code is at https://***/SanchoPanso/tbmsd.

关键词： Training Accuracy Source coding Pipelines Merging Memory management Object detection Robustness Tuning Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Bayesian Inverse Problems with Conditional Sinkhorn Generative Adversarial Networks in Least Volume Latent Spaces

SSRN

引用

SSRN 2024年

作者： Chen, Qiuyi Tsilifis, Panagiotis Fuge, Mark Department of Mechanical Engineering University of Maryland College ParkMD20742 United States Robotics AI & Computer Vision Group General Electric Vernova Advanced Research NiskayunaNY12309 United States

Solving inverse problems in scientific and engineering fields has long been intriguing and holds great potential for many applications, yet most techniques still struggle to address issues such as high dimensionality, nonlinearity and model uncertainty inherent in these problems. Recently, generative models such as Generative Adversarial Networks (GANs) have shown great potential in approximating complex high dimensional conditional distributions and have paved the way for characterizing posterior densities in Bayesian inverse problems, yet the problems’ high dimensionality and high nonlinearity often impedes the model’s training. In this paper we show how to tackle these issues with Least Volume—a novel unsupervised nonlinear dimension reduction method—that can learn to represent the given datasets with the minimum number of latent variables while estimating their intrinsic dimensions. Once the low dimensional latent spaces are identified, efficient and accurate training of conditional generative models becomes feasible, resulting in a latent conditional GAN framework for posterior inference. We demonstrate the power of the proposed methodology on a variety of applications including inversion of parameters in systems of ODEs and high dimensional hydraulic conductivities in subsurface flow problems, and reveal the impact of the observables’ and unobservables’ intrinsic dimensions on inverse problems. © 2024, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Bayesian Inverse Problems with Conditional Sinkhorn Generative Adversarial Networks in Least Volume Latent Spaces

arXiv

引用

arXiv 2024年

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Bayesian Inverse Problems with Conditional Sinkhorn Generative Adversarial Networks in Least Volume Latent Spaces

SSRN

引用

SSRN 2024年

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks for Human-Aware Social Navigation 21st

Graph Neural Networks for Human-Aware Social Navigation

引用

21st International Workshop of Physical Agents, WAF 2020

作者： Manso, Luis J. Jorvekar, Ronit R. Faria, Diego R. Bustos, Pablo Bachiller, Pilar Department of Computer Science College of Engineering and Physical Sciences Aston University Birmingham United Kingdom Department of Computer Engineering Pune Institute of Computer Technology Pune India Robotics and Artificial Vision Laboratory University of Extremadura Badajoz Spain

ISBN: (纸本)9783030625788

Autonomous navigation is a key skill for assistive and service robots. To be successful, robots have to comply with social rules, such as avoiding the personal spaces of the people surrounding them, or not getting in the way of human-to-human and human-to-object interactions. This paper suggests using Graph Neural Networks to model how inconvenient the presence of a robot would be in a particular scenario according to learned human conventions so that it can be used by path planning algorithms. To do so, we propose two automated scenario-to-graph transformations and benchmark them with different Graph Neural Networks using the SocNav1 dataset [1]. We achieve close-to-human performance in the dataset and argue that, in addition to its promising results, the main advantage of the approach is its scalability in terms of the number of social factors that can be considered and easily embedded in code in comparison with model-based approaches. The code used to train and test the resulting graph neural network is available in a public repository. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Absolute Pose from One or Two Scaled and Oriented Features

Absolute Pose from One or Two Scaled and Oriented Features

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Jonathan Ventura Zuzana Kukelova Torsten Sattler Dániel Baráth Department of Computer Science & Software Engineering Cal Poly San Luis Obispo Faculty of Electrical Engineering Visual Recognition Group Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Department of Computer Science Computer Vision and Geometry Group ETH Zürich

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Keypoints used for image matching often include an estimate of the feature scale and orientation. While recent work has demonstrated the advantages of using feature scales and orientations for relative pose estimation, relatively little work has considered their use for absolute pose estimation. We introduce minimal solutions for absolute pose from two oriented feature correspondences in the general case, or one scaled and oriented correspondence given a known vertical direction. Nowadays, assuming a known direction is not particularly restrictive as modern consumer devices, such as smartphones or drones, are equipped with Inertial Measurement Units (IMU) that provide the gravity direction by default. Compared to traditional absolute pose methods requiring three point correspondences, our solvers need a smaller minimal sample, reducing the cost and complexity of robust estimation. Evaluations on large-scale and public real datasets demonstrate the advantage of our methods for fast and accurate localization in challenging conditions. Code is available at https://***/danini/absolute-pose-from-oriented-and-sealed-features.

关键词： Location awareness Accuracy Simultaneous localization and mapping Measurement units Pose estimation Noise Inertial navigation

来源：评论

学校读者我要写书评

暂无评论

Learning Deep Sensorimotor Policies for vision-Based Autonomous Drone Racing

Learning Deep Sensorimotor Policies for Vision-Based Autonom...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Jiawei Fu Yunlong Song Yan Wu Fisher Yu Davide Scaramuzza Department of Informatics Robotics and Perception Group University of Zurich Switzerland Department of Neuroinformatics University of Zurich and ETH Zurich Switzerland Visual Intelligence and Systems Group in the Computer Vision Lab ETH Zurich

The development of effective vision-based algorithms has been a significant challenge in achieving autonomous drones, which promise to offer immense potential for many real-world applications. This paper investigates learning deep sensorimotor policies for vision-based drone racing, which is a particularly demanding setting for testing the limits of an algorithm. Our method combines feature representation learning to extract task-relevant feature representations from high-dimensional image inputs with a learning-by-cheating framework to train a deep sensorimotor policy for vision-based drone racing. This approach eliminates the need for globally-consistent state estimation, trajectory planning, and handcrafted control design, allowing the policy to directly infer control commands from raw images, similar to human pilots. We conduct experiments using a realistic simulator and show that our vision-based policy can achieve state-of-the-art racing performance while being robust against unseen visual disturbances. Our study suggests that consistent feature embeddings are essential for achieving robust control performance in the presence of visual disturbances. The key to acquiring consistent feature embeddings is utilizing contrastive learning along with data augmentation. Video: https://***/AX_fcnW9yqE

关键词：

来源：评论

学校读者我要写书评

暂无评论

Social Space Segmentation for Approaching Tasks

Social Space Segmentation for Approaching Tasks

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Aline F. F. Silva Douglas G. Macharet Department of Computer Science Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais Brazil Laboratório de Inteligência Computacional e Robótica (LICRo) Instituto Federal do Triângulo Mineiro (IFTM) Brazil

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

This paper introduces a novel methodology for the partitioning of the social space associated with arbitrary groups of individuals into approachable regions. The proposed method exploits boundary points within pre-identified social spaces and classifies them into three distinct levels based on the field of view between pairs of individuals within the group. The effectiveness of this approach was rigorously assessed across both static and dynamic scenarios, illustrating successful segmentation and classification of approachable regions. Furthermore, the methodology underwent comprehensive testing using publicly available datasets, yielding consistently satisfactory outcomes. This innovative approach represents a substantial contribution to the field of human-robot interaction, showcasing significant potential for future enhancements and advancements.

关键词： Human-robot interaction Robots Testing

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：