检索结果-内蒙古大学图书馆

26th Computer vision Winter Workshop, CVWW 2023

作者： Šebek, Petr Pokorný, Šimon Vacek, Patrik Svoboda, Tomáš Vision for Robotics and Autonomous Systems Dept. of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague Czech Republic

Object detection and semantic segmentation with the 3D LiDAR point cloud data require expensive annotation. We propose a data augmentation method that takes advantage of already annotated data multiple times. We propose an augmentation framework that reuses real data, automatically finds suitable placements in the scene to be augmented, and handles occlusions explicitly. Due to the usage of the real data, the scan points of newly inserted objects in augmentation sustain the physical characteristics of the LiDAR, such as intensity and raydrop. The pipeline proves competitive in training top-performing models for 3D object detection and semantic segmentation. The new augmentation provides a significant performance gain in rare and essential classes, notably 6.65% average precision gain for "Hard"pedestrian class in KITTI object detection or 2.14 mean IoU gain in the SemanticKITTI segmentation challenge over the state of the art. © 2023 Copyright for this paper by its authors.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking 14

Spectral-Enhanced Transformers: Leveraging Large-Scale Pretr...

引用

14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024

作者： Mohamed, Shaheer Fernando, Tharindu Sridharan, Sridha Moghadam, Peyman Fookes, Clinton Signal Processing Artificial Intelligence and Vision Technologies Queensland University of Technology Brisbane Australia Robotics and Autonomous Systems Data61 CSIRO BrisbaneQLD Australia

ISBN: (纸本)9798331513139

Hyperspectral object tracking using snapshot mosaic cameras is emerging as it provides enhanced spectral information alongside spatial data, contributing to a more comprehensive understanding of material properties. Using transformers, which have consistently outperformed convolutional neural networks (CNNs) in learning better feature representations, would be expected to be effective for Hyperspectral object tracking. However, training large transformers necessitates extensive datasets and prolonged training periods. This is particularly critical for complex tasks like object tracking, and the scarcity of large datasets in the hyperspectral domain acts as a bottleneck in achieving the full potential of powerful transformer models. This paper proposes an effective methodology that adapts large pretrained transformer-based foundation models for hyperspectral object tracking. We propose an adaptive, learnable spatial-spectral token fusion module that can be extended to any transformer-based backbone for learning inherent spatial-spectral features in hyperspectral data. Furthermore, our model incorporates a cross-modality training pipeline that facilitates effective learning across hyperspectral datasets collected with different sensor modalities. This enables the extraction of complementary knowledge from additional modalities, whether or not they are present during testing. Our proposed model also achieves superior performance with minimal training iterations. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Planning Domain Inference for Task and Motion Planning

arXiv

引用

arXiv 2024年

作者： Huang, Jinbang Tao, Allen Marco, Rozilyn Bogdanovic, Miroslav Kelly, Jonathan Shkurti, Florian Space and Terrestrial Autonomous Systems Lab Canada Robot Vision and Learning Lab University of Toronto Robotics Institute Canada

Task and motion planning (TAMP) frameworks address long and complex planning problems by integrating high-level task planners with low-level motion planners. However, existing TAMP methods rely heavily on the manual design of planning domains that specify the preconditions and postconditions of all high-level actions. This paper proposes a method to automate planning domain inference from a handful of test-time trajectory demonstrations, reducing the reliance on human design. Our approach incorporates a deep learning-based estimator that predicts the appropriate components of a domain for a new task and a search algorithm that refines this prediction, reducing the size and ensuring the utility of the inferred domain. Our method is able to generate new domains from minimal demonstrations at test time, enabling robots to handle complex tasks more efficiently. We demonstrate that our approach outperforms behavior cloning baselines, which directly imitate planner behavior, in terms of planning performance and generalization across a variety of tasks. Additionally, our method reduces computational costs and data amount requirements at test time for inferring new planning domains. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Multi-stage Single-Point Incremental Sheet Forming for Enhanced Homogeneous Thickness Distribution

A Multi-stage Single-Point Incremental Sheet Forming for Enh...

引用

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

SPECTRAL-ENHANCED TRANSFORMERS: LEVERAGING LARGE-SCALE PRETRAINED MODELS FOR HYPERSPECTRAL OBJECT TRACKING

arXiv

引用

arXiv 2025年

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Spectral-Enhanced Transformers: Leveraging Large-Scale Pretrained Models for Hyperspectral Object Tracking

Spectral-Enhanced Transformers: Leveraging Large-Scale Pretr...

引用

Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS

作者： Shaheer Mohamed Tharindu Fernando Sridha Sridharan Peyman Moghadam Clinton Fookes Signal Processing Artificial Intelligence and Vision Technologies Queensland University of Technology Brisbane Australia Robotics and Autonomous Systems Data61 CSIRO Brisbane QLD Australia

ISBN: (数字)9798331513139

ISBN: (纸本)9798331513146

关键词： Training Adaptation models Pipelines Transformers Feature extraction Data models Spatial databases Object tracking Hyperspectral imaging Testing

来源：评论

学校读者我要写书评

暂无评论

Robot-based Incremental Forming: Springback Effect Compensation Model for Various Materials *

Robot-based Incremental Forming: Springback Effect Compensat...

引用

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

作者： Walid K. Shaker Alexandr Klimchik Institute of Robotics and Computer Vision Innopolis University Republic of Tatarstan 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

The springback effect refers to the tendency of a material to partially return to its original shape after deformation, especially in incremental metal forming processes. It poses a significant challenge in achieving precise and accurate final shapes, often requiring compensation strategies to reduce its impact. This study focuses on the evaluation and development related to a springback compensation model for incremental sheet metal forming processes. The proposed model aims to optimize toolpaths to counteract springback by addressing deviations between the formed and intended shapes. Performance assessment involved offline numerical simulations using Abaqus/CAE software across various materials. Results demonstrate significant efficacy, with mean error reductions exceeding 60% across different materials. Additionally, the model maintains sheet thickness, preserving material strength during forming.

关键词： Accuracy Shape Deformation Lead Numerical simulation Software Numerical models Magnesium Information technology Robots

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Springback Compensation for Various Profiles in Incremental Forming

Comparative Analysis of Springback Compensation for Various ...

引用

International Russian Automation Conference (RusAutoCon)

作者： Walid K. Shaker Alexandr Klimchik Institute of Robotics and Computer Vision Innopolis University Innopolis Russia Lincoln Centre for Autonomous Systems Research (L-CAS) School of Computer Science University of Lincoln Lincoln United Kingdom

Incremental forming encounters a common challenge known as the springback effect, wherein the workpiece undergoes elastic deformation and deviates slightly from the desired shape once the forming tool is released. This discrepancy between the intended and obtained shape results in reduced geometric accuracy, making incremental forming less precise compared to conventional methods. This research presents a novel springback effect compensation model for sheet forming processes. The main objective is to evaluate the model's performance across various profiles, with a focus on enhancing precision and accuracy in the formed shapes. The proposed model demonstrates an impressive ability to compensate for approximately 60% of the springback effect, offering a practical solution for offline springback compensation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stiffness-based Offline Toolpath Error Compensation for Robotized Incremental Forming

Stiffness-based Offline Toolpath Error Compensation for Robo...

引用

Automation, Control and Robots (ICACR), International Conference on

This paper addresses the challenge of the poor accuracy and the toolpath deviation in Incremental Sheet Forming (ISF) caused by the forming forces applied to the workpiece. The paper proposes an offline toolpath error compensation approach based on stiffness analysis. A truncated cone was used as a test case and the numerical simulation of the ISF process was conducted on Abaqus CAE software to extract forming forces corresponding to toolpath points. The compensation algorithm is based on the Virtual Joint Method (VJM) and is implemented on a FANUC R-2000iC/165F robot using RoboDK API for MATLAB. The results show that the deviation of the robot tool due to the forming forces may reach up to 20 mm which can be handled by the compensated toolpath. Finally, the study proposes an overall process for the stiffness-based correction algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data science and Machine Learning in the clouds: A perspective for the future

arXiv

引用

arXiv 2021年

作者： Barua, Hrishav Bakul Robotics and Autonomous Systems Research Group Cognitive Robotics & Vision TCS Research Kolkata India

As we are fast approaching the beginning of a paradigm shift in the field of science, Data driven science (the so called fourth science paradigm) is going to be the driving force in research and innovation. From medicine to biodiversity and astronomy to geology, all these terms are somehow going to be affected by this paradigm shift. The huge amount of data to be processed under this new paradigm will be a major concern in the future and one will strongly require cloud based services in all the aspects of these computations (from storage to compute and other services). Another aspect will be energy consumption and performance of prediction jobs and tasks within such a scientific paradigm which will change the way one sees computation. Data science has heavily impacted or rather triggered the emergence of Machine Learning, Signal/Image/Video processing related algorithms, Artificial intelligence, robotics, health informatics, geoinformatics, and many more such areas of interest. Hence, we envisage an era where Data science can deliver its promises with the help of the existing cloud based platforms and services with the addition of new services. In this article, we discuss about data driven science and Machine learning and how they are going to be linked through cloud based services in future. It also discusses the rise of paradigms like approximate computing, quantum computing and many more in recent times and their applicability in big data processing, data science, analytics, prediction and machine learning in the cloud *** Codes Artificial intelligence, Data Science, Big data, Data Analytics, Data mining, Machine learning, Deep learning, Cloud computing, Cloud services Copyright © 2021, The Authors. All rights reserved.

关键词： Cloud computing

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：