检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Haoang Meng, Xiangqi Zuo, Xingxing Liu, Zhe Wang, Hesheng Cremers, Daniel Guangzhou China School of Computation Information and Technology Technical University of Munich Munich Germany MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai Jiao Tong University Shanghai China

Simultaneous localization and mapping (SLAM) has achieved impressive performance in static environments. However, SLAM in dynamic environments remains an open question. Many methods directly filter out dynamic objects, resulting in incomplete scene reconstruction and limited accuracy of camera localization. The other works express dynamic objects by point clouds, sparse joints, or coarse meshes, which fails to provide a photo-realistic representation. To overcome the above limitations, we propose a photo-realistic and geometry-aware RGB-D SLAM method by extending Gaussian splatting. Our method is composed of three main modules to 1) map the dynamic foreground including non-rigid humans and rigid items, 2) reconstruct the static background, and 3) localize the camera. To map the foreground, we focus on modeling the deformations and/or motions. We consider the shape priors of humans and exploit geometric and appearance constraints of humans and items. For background mapping, we design an optimization strategy between neighboring local maps by integrating appearance constraint into geometric alignment. As to camera localization, we leverage both static background and dynamic foreground to increase the observations for noise compensation. We explore the geometric and appearance constraints by associating 3D Gaussians with 2D optical flows and pixel patches. Experiments on various real-world datasets demonstrate that our method outperforms state-of-the-art approaches in terms of camera localization and scene representation. Source codes will be publicly available upon paper acceptance. 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

DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior

arXiv

引用

arXiv 2025年

作者： Li, Mingrui Liu, Shuhong Deng, Tianchen Wang, Hongyu the Department of Computer Science Dalian University of Technology Dalian China the Department of Mechano-informatics Information Science and Technology The University of Tokyo Tokyo Japan Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education China

Gaussian SLAM systems excel in real-time rendering and fine-grained reconstruction compared to NeRF-based systems. However, their reliance on extensive keyframes is impractical for deployment in real-world robotic systems, which typically operate under sparse-view conditions that can result in substantial holes in the map. To address these challenges, we introduce DenseSplat, the first SLAM system that effectively combines the advantages of NeRF and 3DGS. DenseSplat utilizes sparse keyframes and NeRF priors for initializing primitives that densely populate maps and seamlessly fill gaps. It also implements geometry-aware primitive sampling and pruning strategies to manage granularity and enhance rendering efficiency. Moreover, DenseSplat integrates loop closure and bundle adjustment, significantly enhancing frame-to-frame tracking accuracy. Extensive experiments on multiple large-scale datasets demonstrate that DenseSplat achieves superior performance in tracking and mapping compared to current state-of-the-art methods. © 2025, CC BY.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Wind Power Prediction Model Based on Seasonal Feature Decomposition and Enhanced Feature Extraction

SSRN

引用

SSRN 2024年

作者： Li, Weipeng Chong, Yuting Guo, Xin Liu, Jun School of Automation and Information Engineering Xi’an University of Technology No. 5 Jinhua South Road Shaanxi Xi’an710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing No. 5 Jinhua South Road Shaanxi Xi’an710048 China

Efficient and accurate wind power prediction is crucial for enhancing the reliability and safety of power system operation and management. The integration of advanced data-driven forecasting methods with precise and efficient data feature decomposition and extraction techniques is necessary to improve the accuracy of wind power generation prediction, due to the inherent randomness and nonlinearity of physical states impacting wind power output, as well as the abundance of redundant information in their original measurement data. This paper proposes a novel hybrid wind power prediction model based on seasonal feature decomposition of wind energy data and enhanced feature extraction. Its effectiveness and superiority are demonstrated through comprehensive multi-model comparisons. © 2024, The Authors. All rights reserved.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

LSU-NET: Lightweight Automatic Organs Segmentation Network for Medical Images

LSU-NET: Lightweight Automatic Organs Segmentation Network f...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yujie Ding Shenghua Teng Zuoyong Li Xiao Chen College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

UNet and its variants have widespread applications in medical image segmentation. However, the substantial number of parameters and computational complexity of these models make them less suitable for use in clinical settings with limited computational resources. To address this limitation, we propose a novel Lightweight Shift U-Net (LSU-Net). We integrate the Light Conv Block and the Tokenized Shift Block in a lightweight manner, combining them with a dynamic weight multi-loss design for efficient dynamic weight allocation. The Light Conv Block effectively captures features with a low parameter count by combining standard convolutions with depthwise separable convolutions. The Tokenized Shift Block optimizes feature representation by shifting and capturing deep features through a combination of the Spatial Shift Block and depthwise separable convolutions. Dynamic adjustment of the loss weights at each layer approaches the optimal solution and enhances training stability. We validated LSU-Net on the UWMGI and MSD Colon datasets, and experimental results demonstrate that LSU-Net outperforms most state-of-the-art segmentation architectures.

关键词： Training Image segmentation Convolution Dynamic scheduling Stability analysis Resource management Speech processing Standards Monitoring Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Extended State Observer Based Fault-Tolerant Predictive control for a Four-Mecanum Wheels Mobile Robot 14

Extended State Observer Based Fault-Tolerant Predictive Cont...

引用

14th IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems, CYBER 2024

作者： Yang, Binghao Wang, Dongliang Wen, Ziling Wei, Wu Li, Wenji Fan, Zhun Shantou University Key Lab of Digital Signal and Image Processing of Guangdong Province Guangdong 515063 China Shantou University School of Department of Electronic and Information Engineering Guangdong 515063 China Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Guangdong Guangzhou510640 China School of Automation Science and Engineering South China University of Technology Guangdong Guangzhou510641 China

ISBN: (纸本)9798331506056

The application of unmanned vehicles in industrial cargo transportation is becoming increasingly widespread, particularly playing a significant role in transporting heavy-duty goods. However, when performing such tasks, whether in single-vehicle transportation or multi-vehicle collaborative transportation, the occurrence of wheel failures can potentially lead to serious safety accidents. Therefore, this paper proposes a fault-tolerant control scheme, establishing a kinematic model considering disturbances and failures, and adopts model predictive control for trajectory tracking. Additionally, an extended state observer is introduced to observe system states and counteract disturbances. To address potential failure issues, a controller reconstruction strategy is proposed. Finally, the effectiveness and superiority of the controller is validated through numerical simulation and comparative experiment. © 2024 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

EEG-GNet: GCN-Based EEG Signal Fatigue Detection Network for Edge Devices

EEG-GNet: GCN-Based EEG Signal Fatigue Detection Network for...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Fuquan Wu, Yu Xu, Xinxin Wang, Chuansheng Ma, Minjia Grau, Antoni Huang, Jiayan School of Computer and Big Data Minjiang University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of New Engineering Industry Putian University Putian China Department of Automatic Control Polytechnic University of Catalonia Barcelona Spain School of Robotics Xi'an Jiaotong-Liverpool University Suzhou China College of New Engineering Industry Putian University Fujian Ruituo Information Technology Limited Company Putian China

ISBN: (纸本)9798350386226

Fatigue driving is a common potential traffic safety hazard. To detect and analysis the driver Fatigue degree in real-time, more attention have been increasing paid to application research of EEG fatigue detection device. However, existing methods suffer from complex model structure or large-scale model parameters. In the other words, they requires high computational consumption and large memory footprint, which creates a contradiction between model and portable EEG machine with limited hardware resources. In this work, we take both time and frequency domains of EEG signal into account and design an lightweight and efficient driver fatigue detection network based on GCN (EEG-GNet), which is available edge-end device application. Experiments on 4th Raspberry Pi on a public baseline dataset show that our EEG-GNet outperforms the state-of-the-art methods and takes good tradeoff between detection accuracy and resource consumption. Our EEG-GNet provides a new potential opportunity for future applications in practical portable/wearable (P/W) devices. © 2024 IEEE.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Localization of Pallets in Narrow Aisles for Unmanned Forklifts 3

Localization of Pallets in Narrow Aisles for Unmanned Forkli...

引用

3rd International Symposium on Computer Technology and information Science, ISCTIS 2023

作者： Sun, Peng Ding, Wei Lian, Mingchang Chen, Hao Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Fujian Fuzhou350108 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China

ISBN: (纸本)9798350325386

As the application of unmanned forklifts becomes more and more widespread, logistics scenarios are constantly evolving. This paper focuses on a scenario where the pick-up of pallets perpendicular to forklift in narrow aisles is required. The narrow aisles only allow the forklift to complete the turning, performing pallet localization in front of it will be difficult. We proposes a method for localizing pallets in narrow aisles for unmanned forklifts. By installing the camera at an oblique angle above the pallet, the collected images are uploaded to the image processing system. The YOLOv5 is used to detect the pallet and extract the bounding boxes of the pallet class. Based on the bounding box coordinates, the original image is cropped. Convert the cropped image to grayscale for Canny edge detection, and then perform Hough line detection to extract the right edge of the pallet. This right edge will be compared with the reference pallet edge to obtain the relative localization between the pallet and the unmanned forklift. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SAR Moving Target Segmentation and Removal Based on Deep Learning 8th

SAR Moving Target Segmentation and Removal Based on Deep L...

引用

8th EAI International Conference on Machine Learning and Intelligent Communications, MLICOM 2023

作者： Wu, Yifan Qi, Xiyu Huang, Lijia Zhang, Bingchen Yan, Lili Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100190 China China Centre for Resources Satellite Data and Application Beijing100094 China

ISBN: (纸本)9783031717154

Synthetic Aperture Radar (SAR) stands as an integral part of advanced remote sensing technology. Nevertheless, practical applications experience inevitable disturbances from moving target noise, compromising both image integrity and target detection performance. This paper introduces a pioneering approach reliant on deep learning principles for the elimination of moving target noise within SAR imaging. Firstly, we use the Back-Projection (BP) algorithm to form the foundational images from echo signals. Employing the Unet network, we subsequently acquire a segmentation map of the moving target noise. By subtracting this segmented noise map from the original image, we succeed in the effective erasure of moving targets, yielding a resultant image devoid of moving target noise. Experimental validation demonstrates that our method can effectively remove moving target noise and yield SAR images that solely contain static scenes. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Real-Time and Fair Resource Allocation for 5G Dense Cellular Networks Based on Deep Reinforcement Learning

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Yong Liu, Zhixin Yuan, Yazhou Guan, Xinping Hebei Key Laboratory of Industrial Computer Control Engineering China Yanshan University Key Laboratory of Intelligent Control and Neural Information Processing Ministry of Education Qinhuangdao066004 China Shanghai Jiaotong University School of Electronic Information and Electrical Engineering Shanghai200240 China

This paper considers a 5G dense cellular network scenario where wireless channels are dynamically changing. To address the resource allocation problems in 5G dense networks, a distributed real-time and fair resource allocation algorithm based on a single deep Q-network (DQN) and multiple local deep neural networks (DNNs) architecture (DRFRA-SDML) is proposed. Specifically, each downlink is modeled as an agent. Each downlink is equipped with a local deep neural network (DNN), allowing each agent to input locally observed information into the local DNN to select spectral subband and transmission power in real-time. In the core network, the global experience replay buffer is utilized to collect local experiences collected by all local agents to train a global weight vector of the train DNN, which is shared by all local DNNs. This ensures that the complexity of the algorithm does not depend on the size of the cellular network, resulting in excellent scalability. To achieve fairness between user devices, a reward function based on fairness has been designed. The simulation results how that, while ensuring fairness between user devices, DRFRA-SDML significantly outperforms IFP-FRA, FP-FRA-D, and Random in both sum rate and real-time performance. © 2014 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed Robust Adaptive control for Cooperative Formation of Uncertain Multiple Fixed-Wing UAVs with Disturbances 5th

Distributed Robust Adaptive Control for Cooperative Formati...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Zhi, Yongran Zheng, Zongzhun Guan, Bin Liu, Lei Fan, Huijin National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Beijing Aerospace Automatic Control Institute Beijing100854 China Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811939976

This paper investigates the formation problem of multiple fixed-wing unmanned aircraft vehicles (UAVs) based on virtual leader structure, subjecting to unknown uncertainties and bounded disturbances. A distributed model reference robust adaptive controller (DMRRAC) is proposed to swiftly construct the formation under the existence of flight dynamical uncertainties and external bounded disturbances. An adaptive projection formation operator and a novel high-frequency robust term can guarantee the system to be uniformly asymptotically stable in a complex situation, which can also enhance the performance of the system such as robustness. Simulation confirms the feasibility and effectiveness of the proposed distributed control algorithm. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fixed wings

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：