检索结果-内蒙古大学图书馆

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Ghadeer Issa Karam Almaghout Alexander Maloletov Alexandr Klimchik Intelligent Robotics Systems Laboratory Institute of Robotics and Computer Vision Innopolis University Innopolis Russia Lincoln Centre for Autonomous Systems (L-CAS) School of Computer Science University of Lincoln Lincoln United Kingdom

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

This paper introduces a multi-stage approach to enhance homogeneous thickness distribution in single-point incremental sheet forming. Traditional methods often struggle with achieving uniform material thickness, compromising the final part’s structural integrity and performance. Our proposed methodology leverages a V-shape starting stage, systematically designed to address these challenges by improving material flow and distribution throughout the forming process. We employ finite element analysis to validate the efficiency of the proposed approach and compare it with conventional single-stage forming processes. The simulations demonstrate significant improvements in achieving a more uniform thickness distribution across the formed parts. The comparative analysis highlights the potential of the proposed multi-stage approach for industrial applications and enhances material homogeneity. This methodology advances the precision and reliability of formed parts and opens new avenues for research and development in sheet metal forming technologies.

关键词： Geometry Accuracy Shape Simulation Metals Production Manufacturing Reliability Information technology Research and development

来源：评论

学校读者我要写书评

暂无评论

Exploiting autoencoder’s weakness to generate pseudo anomalies

引用

Neural Computing and Applications 2024年第23期36卷 14075-14091页

作者： Astrid, Marcella Zaheer, Muhammad Zaigham Aouada, Djamila Lee, Seung-Ik Department of Artificial Intelligence University of Science and Technology Daejeon34113 Korea Republic of Field Robotics Research Section Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Interdisciplinary Centre for Security Reliability and Trust University of Luxembourg Luxembourg1855 Luxembourg Department of Computer Vision Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

Due to the rare occurrence of anomalous events, a typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal training data. At test time, the trained AE is expected to well reconstruct normal but to poorly reconstruct anomalous data. However, contrary to the expectation, anomalous data are often well reconstructed as well. In order to further separate the reconstruction quality between normal and anomalous data, we propose creating pseudo anomalies from learned adaptive noise by exploiting the aforementioned weakness of AE, i.e., reconstructing anomalies too well. The generated noise is added to the normal data to create pseudo anomalies. Extensive experiments on Ped2, Avenue, ShanghaiTech, CIFAR-10, and KDDCUP datasets demonstrate the effectiveness and generic applicability of our approach in improving the discriminative capability of AEs for anomaly detection. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer 24

Frequency Guidance Matters: Skeletal Action Recognition by F...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Wenhan Zheng, Ce Yang, Zihao Chen, Chen Das, Srijan Lu, Aidong Department of Computer Science University of North Carolina at Charlotte CharlotteNC United States Robotics Institute Carnegie Mellon University PittsburghPA United States One Inventory Organization Microsoft Corporation RedmondWA United States Center for Research in Computer Vision University of Central Florida OrlandoFL United States

ISBN: (纸本)9798400706868

Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action recognition. However, the existing transformer-based approaches heavily rely on the naive attention mechanism for capturing the spatiotemporal features, which falls short in learning discriminative representations that exhibit similar motion patterns. To address this challenge, we introduce the Frequency-aware Mixed Transformer (FreqMixFormer), specifically designed for recognizing similar skeletal actions with subtle discriminative motions. First, we introduce a frequency-aware attention module to unweave skeleton frequency representations by embedding joint features into frequency attention maps, aiming to distinguish the discriminative movements based on their frequency coefficients. Subsequently, we develop a mixed transformer architecture to incorporate spatial features with frequency features to model the comprehensive frequency-spatial patterns. Additionally, a temporal transformer is proposed to extract the global correlations across frames. Extensive experiments show that FreqMiXFormer outperforms SOTA on 3 popular skeleton action recognition datasets, including NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets. Our project is publicly available at: https://***/wenhanwu95/FreqMixFormer. © 2024 ACM.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Real-time FPGA implementation of the Semi-Global Matching stereo vision algorithm for a 4K/UHD video stream

TechRxiv

引用

TechRxiv 2023年

作者： Grabowski, Mariusz Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

In this paper, we propose a real-time FPGA implementation of the Semi-Global Matching (SGM) stereo vision algorithm. The designed module supports a 4K/Ultra HD (3840×2160 pixels @ 30 frames per second) video stream in a 4 pixel per clock (ppc) format and a 64-pixel disparity range. The baseline SGM implementation had to be modified to process pixels in the 4ppc format and meet the timing constrains, however, our version provides results comparable to the original design. The solution has been positively evaluated on the Xilinx VC707 development board with a Virtex-7 FPGA device. © 2023, CC BY.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Real-time FPGA implementation of the Semi-Global Matching stereo vision algorithm for a 4K/UHD video stream

arXiv

引用

arXiv 2023年

作者： Grabowski, Mariusz Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics Agh University of Science and Technology Krakow Poland

In this paper, we propose a real-time FPGA implementation of the Semi-Global Matching (SGM) stereo vision algorithm. The designed module supports a 4K/Ultra HD (3840 ×2160 pixels @ 30 frames per second) video stream in a 4 pixel per clock (ppc) format and a 64-pixel disparity range. The baseline SGM implementation had to be modified to process pixels in the 4ppc format and meet the timing constrains, however, our version provides results comparable to the original design. The solution has been positively evaluated on the Xilinx VC707 development board with a Virtex-7 FPGA device. © 2023, CC BY.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Explicit Model Predictive Control Design based on Constrained Zonotope Propagation

Explicit Model Predictive Control Design based on Constraine...

引用

School on Dynamics of Complex Networks and their Application in Intellectual robotics (DCNAIR)

作者： Ali Jnadi Ramil Khusainov Simeon Nedelchev Sergei Savin Institute of Robotics and Computer Vision Innopolis University Innopolis Russia Center for Technologies in Robotics and Mechatronics Components Innopolis University Innopolis Russia

Zonotopes have become a widely used tool in control design, demonstrating their effectiveness in various applications ranging from state estimation to explicit model predictive control. However, the traditional use of zonotopes is limited by a set certain geometric shapes that restrict the range of state sets that can be considered. This paper proposes a novel approach to control design using constrained zonotopes that can encode arbitrary polytopes. We present a propagation scheme and an affine approximation of the exact control law for this representation, and discuss issues related to center identification for constrained zonotopes. A fast method for detecting set membership is also proposed based on lifting the constrained zonotopes into a higher dimensional space. The proposed method extends the range of shapes that can be considered in control design and offers a promising alternative to the limitations of regular zonotopes. It has the potential for wide-ranging impact in various areas of control, providing a valuable tool for solving complex control problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ELK: Enhanced Learning Through Cross-Modal Knowledge Transfer for Lesion Detection in Limited-Sample Contrast-Enhanced Mammography Datasets 1st

ELK: Enhanced Learning Through Cross-Modal Knowledge Transfe...

引用

1st Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care, Deep-Breath 2024

作者： Montoya-del-Angel, Ricardo Elbatel, Marawan Castillo-Lopez, Jorge Patricio Villaseñor-Navarro, Yolanda Brandan, Maria-Ester Marti, Robert Computer Vision and Robotics Institute University of Girona Girona Spain The Hong Kong University of Science and Technology Hong Kong Instituto Nacional de Cancerología Mexico City Mexico Instituto de Física Universidad Nacional Autónoma de México Mexico City Mexico

ISBN: (纸本)9783031777882

Contrast-enhanced mammography (CEM) offers improved breast cancer diagnosis by enhancing vascular contrast uptake. However, the development of reliable deep learning-based computer-aided detection (CAD) systems for CEM is hindered by limited data availability. This paper introduces ELK (Enhanced Learning through cross-modal Knowledge transfer), a deep learning pipeline designed to adapt large pre-trained models into a target limited data-volume population by leveraging synthetic data augmentation. Specifically, we adapt a detection model pretrained on digital breast tomosynthesis (DBT) and digital mammography data into a target CEM population using diffusion models to generate high-resolution, realistic synthetic lesions, preserving the visual integrity of CEM images. To assess the efficacy of our synthetic lesions, we compare the detection performance of a pretrained Faster R-CNN detector fine-tuned using only real images, synthetic images, and a combination of both. Our approach improves mean sensitivity by 4% on a test sample from the same population and by 7% on a newly collected out-of-domain CEM dataset. Our code and synthetic datasets are available at https://***/Likalto4/CEM-Detect. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences

arXiv

引用

arXiv 2023年

作者： Pataki, Zador Altillawi, Mohammad Kanakis, Menelaos Pautrat, Rémi Shen, Fengyi Liu, Ziyuan Van Gool, Luc Pollefeys, Marc The Computer Vision and Geometry Lab Department of Computer Science ETH Zurich Switzerland The Computer Vision Center CVC-Barcelona The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Computer Vision Lab Department Electrical Engineering ETH Zurich Switzerland The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Intelligent Robotics Cloud Technology lab of Huawei-Munich Germany The Center for Processing Speech and Images KU Leuven The Computer Vision Lab ETH Zurich Switzerland

Modern learning-based visual feature extraction networks perform well in intra-domain localization, however, their performance significantly declines when image pairs are captured across long-term visual domain variations, such as different seasonal and daytime variations. In this paper, our first contribution is a benchmark to investigate the performance impact of long-term variations on visual localization. We conduct a thorough analysis of the performance of current state-of-the-art feature extraction networks under various domain changes and find a significant performance gap between intra- and cross-domain localization. We investigate different methods to close this gap by improving the supervision of modern feature extractor networks. We propose a novel data-centric method, Implicit Cross-Domain Correspondences (iCDC). iCDC represents the same environment with multiple Neural Radiance Fields, each fitting the scene under individual visual domains. It utilizes the underlying 3D representations to generate accurate correspondences across different long-term visual conditions. Our proposed method enhances cross-domain localization performance, significantly reducing the performance gap. When evaluated on popular long-term localization benchmarks, our trained networks consistently outperform existing methods. This work serves as a substantial stride toward more robust visual localization pipelines for long-term deployments, and opens up research avenues in the development of long-term invariant descriptors. Copyright © 2023, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

FrontierNet: Learning Visual Cues to Explore

引用

IEEE robotics and Automation Letters 2025年第7期10卷 6576-6583页

作者： Sun, Boyang Chen, Hanzhi Leutenegger, Stefan Cadena, Cesar Pollefeys, Marc Blum, Hermann ETH Zurich Computer Vision and Geometry Group Zurich8092 Switzerland Technical University of Munich Mobile Robotics Lab München80333 Germany ETH Zurich Mobile Robotics Lab Zurich8092 Switzerland ETH Zurich Robotic Systems Lab Zurich8092 Switzerland AI Lab Microsoft Mixed Reality Zurich8038 Switzerland University of Bonn Lamarr Institute for ML and AI Robot Perception and Learning Lab Bonn53115 Germany

Exploration of unknown environments is crucial for autonomous robots;it allows them to actively reason and decide on what new data to acquire for different tasks, such as mapping, object discovery, and environmental assessment. Existing solutions, such as frontier-based exploration approaches, rely heavily on 3D map operations, which are limited by map quality and, more critically, often overlook valuable context from visual cues. This work aims at leveraging 2D visual cues for efficient autonomous exploration, addressing the limitations of extracting goal poses from a 3D map. We propose a visual-only frontier-based exploration system, with FrontierNet as its core component. FrontierNet is a learning-based model that (i) proposes frontiers, and (ii) predicts their information gain, from posed RGB images enhanced by monocular depth priors. Our approach provides an alternative to existing 3D-dependent goal-extraction approaches, achieving a 15% improvement in early-stage exploration efficiency, as validated through extensive simulations and real-world experiments. © 2016 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Simulation Study for Robot-based Single Point Incremental Forming

Simulation Study for Robot-based Single Point Incremental Fo...

引用

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

作者： Walid K. Shaker Alexandr Klimchick Institute of Robotics and Computer Vision Innopolis University Innopolis Russia School of Computer Science University of Lincoln Lincoln United Kingdom

The present study investigates the toolpath definition for the numerical simulation of the Single Point Incremental Forming (SPIF). Since the toolpath definition greatly influences the geometrical accuracy of the formed part, substantial research has been taken to properly generate the toolpath. In this paper, two different toolpath strategies were defined: Z-level, and spiral toolpath. A robot program was created using RoboDK to simulate the SPIF process and to test the generated toolpath over a designed workpiece of a truncated cone. The paper also shows how the SPIF numerical simulation was conducted on Abaqus/CAE software. The results demonstrated that the toolpath was properly designed; however, 0.5% relative error was found between the desired and the simulated cone depth due to the SPIF geometric error. To improve the overall accuracy of the SPIF, a combined stiffness-based and closed loop control algorithm is proposed.

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：