检索结果-内蒙古大学图书馆

Sector Patch Embedding: An Embedding Module Conforming to The Distortion Pattern of Fisheye Image

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Dianyi Tang, Jiadong Gao, Yu Yang, Yi Fu, Mengyin School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China

Fisheye cameras suffer from image distortion while having a large field of view(LFOV). And this fact leads to poor performance on some fisheye vision tasks. One of the solutions is to optimize the current vision algorithm for fisheye images. However, most of the CNN-based methods and the Transformer-based methods lack the capability of leveraging distortion information efficiently. In this work, we propose a novel patch embedding method called Sector Patch Embedding(SPE), conforming to the distortion pattern of the fisheye image. Furthermore, we put forward a synthetic fisheye dataset based on the ImageNet-1K and explore the performance of several Transformer models on the dataset. The classification top-1 accuracy of ViT and PVT is improved by 0.75% and 2.8% with SPE respectively. The experiments show that the proposed sector patch embedding method can better perceive distortion and extract features on the fisheye images. Our method can be easily adopted to other Transformer-based models. Source code is at https://***/IN2-ViAUn/Sector-Patch-Embedding. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Fireclay

Dynamic Performance Prediction in Batch-Based Assembly system with Bernoulli Machines and Changeovers

学校读者我要写书评

暂无评论

Complex system Modeling and Simulation 2022年第3期2卷 224-237页

作者： Zunjun Wang Zhiyang Jia Xiuxuan Tian Jingchuan Chen Bei Pan State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China Department of Industrial and Manufacturing Systems Engineering University of Hong KongHong Kong 999077China School of Engineering Tokyo University of TechnologyTokyo 192-0982Japan

Worldwide competition and diverse demand of customers pose great challenges to manufacturing enterprises. How to organize production to achieve high productivity and low cost becomes their primary task. In the mean time, the rapid pace of technology innovation has contributed to the development of new types of flexible automation. Hence, increasing manufacturing enterprises convert to multi-product and small-batch production, a manufacturing strategy that brings increased output, reduced costs, and quick response to the market. A distinctive feature of small-batch production is that the system operates mainly in the transient states. Transient states may have a significant impact on manufacturing systems. It is therefore necessary to estimate the dynamic performance of systems. As the assembly system is a typical class of production systems, in this paper, we focus on the problem of dynamic performance prediction of the assembly systems that produce small batches of different types of products. And the system is assumed to be characterized with Bernoulli reliability machines, finite buffers, and changeovers. A mathematical model based on Markovian analysis is first derived and then, the analytical formulas for performance evaluation of three-machine assembly systems are given. Moreover, a novel approach based on decomposition and aggregation is proposed to predict dynamic performance of large-scale assembly systems that consist of multiple component lines and additional processing machines located downstream of the assemble machine. The proposed approach is validated to be highly accurate and computationally efficient when compared to Monte Carlo simulation.

关键词： flexible assembly system dynamic performance Bernoulli machines finite buffers changeovers

DR-WLC: Dimensionality Reduction cognition for object detection and pose estimation by Watching, Learning and Checking

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gao, Yu Xu, Xi Jiang, Tianji Chen, Siyuan Yang, Yi Yue, Yufeng Fu, Mengyin School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China

Object detection and pose estimation are difficult tasks in robotics and autonomous driving. Existing object detection and pose estimation methods mostly adopt the same-dimensional data for training. For example, 2D object detection usually requires a large amount of 2D annotation data with high cost. Using high-dimensional information to supervise lower-dimensional tasks is a feasible way to reduce datasets size. In this work, the DR-WLC, a dimensionality reduction cognitive model, which can perform both object detection and pose estimation tasks at the same time is proposed. The model only requires 3D model of objects and unlabeled environment images (with or without objects) to finish the training. In addition, a bounding boxes generation strategy is also proposed to build the relationship between 3D model and 2D object detection task. Experiments show that our method can qualify the work without any manual annotations and it is easy to deploy for practical applications. Source code is at https: //***/IN2-ViAUn/DR-WLC. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

CRRS: Concentric Rectangles Regression Strategy for Multi-point Representation on Fisheye Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xihan Xu, Xi Gao, Yu Yang, Yi Yue, Yufeng Fu, Mengyin School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China

Modern object detectors take advantage of rectangular bounding boxes as a conventional way to represent objects. When it comes to fisheye images, rectangular boxes involve more background noise rather than semantic information. Although multi-point representation has been proposed, both the regression accuracy and convergence still perform inferior to the widely used rectangular boxes. In order to further exploit the advantages of multi-point representation for distorted images, Concentric Rectangles Regression Strategy(CRRS) is proposed in this work. We adopt smoother mean loss to allocate weights and discuss the effect of hyper-parameter to prediction results. Moreover, an accurate pixel-level method is designed to obtain irregular IoU for estimating detector performance. Compared with the previous work for muti-point representation, the experiments show that CRRS can improve the training performance both in accurate and stability. We also prove that multi-task weighting strategy facilitates regression process in this design. Source code is at https://***/IN2-ViAUn/Concentric-Rectangles-Loss. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

MC-NeRF: Multi-Camera Neural Radiance Fields for Multi-Camera Image Acquisition systems

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gao, Yu Su, Lutong Liang, Hao Yue, Yufeng Yang, Yi Fu, Mengyin School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China

Neural Radiance Fields (NeRF) use multi-view images for 3D scene representation, demonstrating remarkable performance. As one of the primary sources of multi-view images, multi-camera systems encounter challenges such as varying intrinsic parameters and frequent pose changes. Most previous NeRF-based methods assume a unique camera and rarely consider multi-camera scenarios. Besides, some NeRF methods that can optimize intrinsic and extrinsic parameters still remain susceptible to suboptimal solutions when these parameters are poor initialized. In this paper, we propose MC-NeRF, a method that enables joint optimization of both intrinsic and extrinsic parameters alongside NeRF. The method also supports each image corresponding to independent camera parameters. First, we tackle coupling issue and the degenerate case that arise from the joint optimization between intrinsic and extrinsic parameters. Second, based on the proposed solutions, we introduce an efficient calibration image acquisition scheme for multi-camera systems, including the design of calibration object. Finally, we present an end-to-end network with training sequence that enables the estimation of intrinsic and extrinsic parameters, along with the rendering network. Furthermore, recognizing that most existing datasets are designed for a unique camera, we construct a real multi-camera image acquisition system and create a corresponding new dataset, which includes both simulated data and real-world captured images. Experiments confirm the effectiveness of our method when each image corresponds to different camera parameters. Specifically, we use multi-cameras, each with different intrinsic and extrinsic parameters in real-world system, to achieve 3D scene representation without providing initial poses. The Code and supplementary materials are available at https://***/MC-NeRF Copyright © 2023, The Authors. All rights reserved.

关键词： Parameter estimation

Review on recent progress in on-line monitoring technology for atmospheric pollution source emissions in China

学校读者我要写书评

暂无评论

Journal of Environmental Sciences 2023年第1期123卷 367-386页

作者： Huanqin Wang Jitong Zhou Xue Li Qiang Ling Hongyuan Wei Lei Gao Ying He Ming Zhu Xiao Xiao Youjiang Liu Shan Li Chilai Chen Guotao Duan Zhimin Peng Peili Zhou Yufeng Duan Jianbing Wang Tongzhu Yu Yixin Yang Jiguang Wang Zhen Zhou Huaqiao Gui Yanjun Ding State Key Laboratory of Transducer Technology Institute of Intelligent MachinesHefei Institutes of Physical ScienceChinese Academy of SciencesHefei 230031China Institute of Mass Spectrometry and Atmospheric Environment Jinan UniversityGuangzhou 510632China Department of Automation University of Science and Technology of ChinaHefei 230027China China Automotive Technology and Research Center Tianjin 300300China Institute of Solid State Physics Chinese Academy of SciencesHefei 230031China Key Laboratory of Environmental Optics and Technology Anhui Institute of Optics and Fine MechanicsChinese Academy of SciencesHefei 230031China School of Electronic Information and Communications Huazhong University of Science and TechnologyWuhan 430074China School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Power Systems Department of Energy and Power EngineeringTsinghua UniversityBeijing 100084China Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education School of Energy and EnvironmentSoutheast UniversityNanjing 210096China School of Chemical and Environmental Engineering China University of Mining and Technology(Beijing)Beijing 100083China CAS Center for Excellence in Regional Atmospheric Environment Institute of Urban EnvironmentChinese Academy of SciencesXiamen 361021China

Emissions from mobile sources and stationary sources contribute to atmospheric pollution in China,and its components,which include ultrafine particles(UFPs),volatile organic compounds(VOCs),and other reactive gases,such as NH3and NOx,are the most harmful to human *** has released various regulations and standards to address pollution from mobile and stationary ***,it is urgent to develop online monitoring technology for atmospheric pollution source *** study provides an overview of the main progress in mobile and stationary source monitoring technology in China and describes the comprehensive application of some typical instruments in vital areas in recent *** instruments have been applied to monitor emissions from motor vehicles,ships,airports,the chemical industry,and electric power *** only has the level of atmospheric environment monitoring technology and equipment been improving,but relevant regulations and standards have also been constantly ***,the developed instruments can provide scientific assistance for the successful implementation of *** to the potential problem areas in atmospheric pollution in China,some research hotspots and future trends of atmospheric online monitoring technology are ***,more advanced atmospheric online monitoring technology will contribute to a comprehensive understanding of atmospheric pollution and improve environmental monitoring capacity.

关键词： Atmospheric pollution Mobile sources Stationary sources On-line monitoring technology

Variable stiffness design optimization of fiber-reinforced composite laminates with regular and irregular holes considering fiber continuity for additive manufacturing

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2025年第3期38卷 334-354页

作者： Yi LIU Zunyi DUAN Chunping ZHOU Yuan SI Chenxi GUAN Yi XIONG Bin XU Jun YAN Jihong ZHU School of Mechanics Civil Engineering&ArchitectureNorthwestern Polytechnical UniversityXi’an 710072China Research&Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen 518063China Key Lab for Airborne Hi-performance Electro-magnetic Window RISACJinan 130012China School of System Design and Intelligent Manufacturing Southern University of Science and TechnologyShenzhen 518055China State Key Laboratory of Structural Analysis for Industrial Equipment Department of Engineering MechanicsInternational Research Center for Computational MechanicsDalian University of TechnologyDalian 116024China State IJR Center of Aerospace Design and Additive Manufacturing MIIT Lab of Metal Additive Manufacturing and Innovative DesignNorthwestern Polytechnical UniversityXi’an 710072China

Fiber-reinforced composites are an ideal material for the lightweight design of aerospace structures. Especially in recent years, with the rapid development of composite additive manufacturing technology, the design optimization of variable stiffness of fiber-reinforced composite laminates has attracted widespread attention from scholars and industry. In these aerospace composite structures, numerous cutout panels and shells serve as access points for maintaining electrical, fuel, and hydraulic systems. The traditional fiber-reinforced composite laminate subtractive drilling manufacturing inevitably faces the problems of interlayer delamination, fiber fracture, and burr of the laminate. Continuous fiber additive manufacturing technology offers the potential for integrated design optimization and manufacturing with high structural performance. Considering the integration of design and manufacturability in continuous fiber additive manufacturing, the paper proposes linear and nonlinear filtering strategies based on the Normal Distribution Fiber Optimization (NDFO) material interpolation scheme to overcome the challenge of discrete fiber optimization results, which are difficult to apply directly to continuous fiber additive manufacturing. With minimizing structural compliance as the objective function, the proposed approach provides a strategy to achieve continuity of discrete fiber paths in the variable stiffness design optimization of composite laminates with regular and irregular holes. In the variable stiffness design optimization model, the number of candidate fiber laying angles in the NDFO material interpolation scheme is considered as design variable. The sensitivity information of structural compliance with respect to the number of candidate fiber laying angles is obtained using the analytical sensitivity analysis method. Based on the proposed variable stiffness design optimization method for complex perforated composite laminates, the numerical examples cons

关键词： Variable stiffness composite laminates Discrete material interpolation scheme Normal distribution fiber optimization Discrete fiber continuous filtering strategy Additive manufacturing of composite laminates

Application of Deep Learning Method to Estimate Bottomhole Pressure Dynamics of Oil Wells 32

学校读者我要写书评

暂无评论

Application of Deep Learning Method to Estimate Bottomhole P...

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Cheng, Haibo Li, Shichao Zeng, Peng Vyatkin, Valeriy State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Luleå University of Technology Electrical and Space Engineering Department of Computer Science Luleå Sweden Aalto University Department of Electrical Engineering and Automation Helsinki Finland

ISBN: (纸本)9798350399714

Surrogate models, which have become an effective and popular method to close loop reservoir management problems, use a data-driven approach to predict dynamic injection and production wells parameters and optimize waterflooding development. In this study, a deep learning-based surrogate model method is proposed to estimate bottomhole pressure (BHP) of production wells in waterflooding reservoirs. Bidirectional long short-term memory (BiLSTM) network, as an efficient deep learning approach, is applied to BHP estimation using fluctuation data. Extended Fourier amplitude sensitivity test (EFAST) method is employed to analyse the influence of different input factors on BHP dynamics, and a reduced dataset is rebuilt to predict BHP parameter based on BiLSTM-EFAST algorithm. The estimation results are tested on a dataset from Volve oilfield in North Sea, and compared with other deep learning methods. The test results indicate that the proposed method can achieve higher prediction accuracy. A reduced dataset-based approach provides a new attempt to reduce model complexity and improve calculation speed for big data-driven surrogate model in oil and gas industry. © 2023 IEEE.

关键词： Long short-term memory