检索结果-内蒙古大学图书馆

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Chen, Chen Hu, Song-Tao Wei, Yue-Nan Shu, Zhong-Cheng Liu, Liu School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China Henan Transport Investment Group Co. Ltd. Zhengzhou China

ISBN: (纸本)9789819639601

Ship instance segmentation technology is becoming more and more important in applications such as ship identification, monitoring and tracking, which is of great significance for maritime safety management. However, due to the different shapes of ships, as well as the complexity and volatility of illumination, weather and other factors, the existing ship instance segmentation methods are often difficult to achieve good segmentation results. To address this problem, this paper proposes a real-time segmentation method for ship instances based on contours that uses CenterNet algorithm to detect ship targets. The core network uses DLA-34 (Deep Layer Aggregation) to ensure the detection accuracy and speed. Then, the Deep Snake method is used to segment the ship object accurately. In order to verify the effectiveness of the proposed algorithm, this study constructed a dedicated dataset of 2300 images involving complex environments such as inland rivers and ports under three typical conditions: day, night, and haze. In addition, this dataset was used to test the proposed method, and the average recall (AR) rate was 95.5% and the average precision (AP) rate was 93.1%. The proposed method can achieve the inference performance of 47 frames per second on the RTX3090 GPU. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Underground low-light self-supervised image enhancement method based on structure and texture perception

引用

Meitan Xuebao/Journal of the China Coal Society 2025年第4期50卷 2310-2320页

作者： Pan, Shan Yu, Ting Chen, Wei Tian, Zijian Yue, Zhongwen Beijing100083 China School of Computer Science & Technology China University of Mining and Technology Xuzhou221000 China Key Laboratory of Coal Mine Intelligent Robot Innovation Emergency Management Department Xuzhou221000 China Beijing100083 China

Due to the complex spatial environment and uneven artificial lighting underground, images captured by underground visual equipment often suffer from insufficient overall or partial lighting and poor visibility of image content. Existing image enhancement methods for low-light underground images often result in poor contrast and issues with overexposure and underexposure in certain areas. Within this article, we propose a self-supervised image enhancement method for low-light underground conditions based on structural and texture perception, aiming to alleviate the dependence on paired low-light/normal-light images during training. Firstly, to generate smoothly segmented illumination maps, we design a self-supervised structural and texture-aware illumination estimation network, which preserves scene edge structures and smooths texture details based on self-supervised training losses. To further exploit local texture features and global structural features in low-light images to improve the performance of the illumination estimation network, we introduce a local-global perception module into the illumination estimation network. This module leverages the ability of convolutional operations with small receptive fields to capture local features and the self-attention mechanism of visual transformers to facilitate global information interaction, thus extracting local and global features from low-light images. Secondly, to facilitate self-supervised learning, we adopt a structure-aware smoothness loss considering the segmented smoothness property of illumination maps. Finally, to refine the illumination maps generated by the illumination estimation network for reasonable brightness and contrast, we introduce a pseudo-label image generator to synthesize pseudo-label images with good contrast and brightness. By constraining the consistency between brightness and contrast of the enhanced images and pseudo-label images through reconstruction loss, we indirectly constrain the i

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

FourCornerGAN: Glyph formation augmentation for unpaired Chinese font generation

引用

Digital Signal Processing: A Review Journal 2025年 165卷

作者： Wang, Kaili Zhou, Chi Shi, Yuanlin Wu, Tianquan Chen, Chen Hubei Key Laboratory of Intelligent Robot School of Computer Science and Engineering Wuhan Institute of Technology Hubei Wuhan430205 China

Chinese character font generation poses unique challenges due to the complexity of glyph structures and the scarcity of paired training data. Existing methods for Chinese character font generation often suffer from issues like missing glyph formation and insufficient detail. To overcome these limitations, combining with the spatial glyph formation information, a novel encoding method based on the Four-Corner Number is proposed and integrated into CycleGAN to develop into FourCornerGAN to enhance structural representation in unpaired Chinese font generation, and a new Four-Corner Consistency Loss is introduced to guide both the generator and discriminator in preserving spatial glyph formation details. Extensive experiments demonstrate that FourCornerGAN significantly improves generation quality over baseline models, particularly in structural accuracy and visual consistency. This approach offers a promising solution for high-fidelity font synthesis without paired samples. Code and dataset are available at https://***/nini739/FourCornerGAN. © 2025 Elsevier Inc.

关键词： Font generation Four-corner encoding Generative adversarial networks Image-to-image translation

来源：评论

学校读者我要写书评

暂无评论

The research of distributed CO2 monitoring technology based on NB-IoT 4

The research of distributed CO2 monitoring technology based ...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Hu, Chun Li, Yanlin Zheng, Dezhi Cheng, Yufei Peng, Peng Nie, Sichong Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of Technology Beijing100081 China MIIT Key Laboratory of Complex-field Intelligent Exploration Beijing Institute of Technology Beijing100081 China State Key Laboratory of CNS/ATM Beijing Institute of Technology Beijing100081 China Chongqing Caeri Robot Technology Co. Ltd. Certification Department Chongqing400722 China Innovation&Research Institute of HIWING Technology Academy Beijing100074 China

ISBN: (纸本)9781510688834

CO2 is one of the primary contributors to the greenhouse effect, and its monitoring and control are critical for achieving carbon peaking and neutrality goals. Therefore, large-scale distributed monitoring of CO2 concentrations in the environment is of significant importance. To investigate the diffusion patterns of CO2 in windless environments, this paper designs and implements a distributed CO2 monitoring system. The system adopts the three-layer architecture of the Internet of Things (IoT) as its overall framework, utilizing a self-developed CO2 sensor as the sensing layer node. The system employs the Narrowband Internet of Things (NB-IoT) protocol to achieve multi-node, wide-coverage, and low-power data transmission and reception. A custom database is developed as the application layer to store, classify, and manage data collected by the nodes. Experimental results provide CO2 monitoring data, which are analyzed to summarize the variation patterns of CO2 concentration over time and distance. By comparing these results with existing gas diffusion models, it is found that the trends are consistent, thereby demonstrating the reliability and stability of the proposed system. © 2025 SPIE.

关键词： Carbon capture and utilization

来源：评论

学校读者我要写书评

暂无评论

Distributed Source Localization Under Anchor Position Uncertainty

引用

Chinese Journal of Electronics 2025年第1期23卷 93-96页

作者： Hongqing Liu Yuntao Wu Department of Electronic and Computer Engineering National University of Singapore Singapore Key Laboratory of Intelligent Robot in Hubei Province Wuhan Institute of Technology Wuhan China

In this work, a distributed source positioning approach is developed based on Alternating direction method of multipliers (ADMM). First, a centralized positioning method is developed under case of the anchor uncertainty. And then, the method is realized in a distributed way using ADMM. Simulation results show that the centralized one is robust to the anchor errors and distributed one has similar performance as the centralized one.

关键词： Location awareness Uncertainty Codes Simulation robot sensing systems Convex functions intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Deep optics framework utilizing a liquid crystal microlens array for dynamic wavefront sensing and correction in atmospheric turbulence

引用

Optics Letters 2025年第11期50卷 3584-3587页

作者： Xiaoyue Song Hui Li Zikang Li Shiqi Li Yuntao Wu School of Computer Science and Engineering Wuhan Institute of Technology Wuhan 430205 China Hubei Key Laboratory of Intelligent Robot Wuhan 430205 China ytwu@***

Anisotropic atmospheric turbulence, which distorts wavefronts, poses challenges to advancements in fields such as astronomy and remote sensing. Existing reconstruction methods often fail to adequately capture its spatiotemporal variability, leading to suboptimal performance. To address this, we propose a spatiotemporal quantization-aware deep optics framework. This framework integrates light field physics models with a data-driven neural network via a liquid crystal microlens array (LC-MLA), offering a solution to dynamic turbulence issues. The framework constructs a spatiotemporal transfer function that integrates wavefront sensing, high-dimensional spatiotemporal quantization-aware turbulence modeling, and neural network characterization. By synergizing dynamic light field data with electronically tunable LC-MLA, our approach optimizes hardware and software parameters for efficient, precise correction of multi-field, multi-order aberrations. In experiments, this approach optimizes real-time turbulence correction and offers a 17.5% improvement in peak signal-to-noise ratio compared to previous methods.

关键词： Atmospheric correction Atmospheric turbulence Liquid crystals Microlens arrays Remote sensing Wave front sensing

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition of sEMG Based on Res-LSTM 17th

Gesture Recognition of sEMG Based on Res-LSTM

引用

17th International Conference on intelligent robotics and Applications, ICIRA 2024

作者： Zhao, Yujia Zou, Chunlong Yun, Juntong Jiang, Du Huang, Li Liu, Ying Jiang, Guozhang Xie, Yuanmin Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China College of Mechanical Engineering Hubei University of Automotive Technology Shiyan442000 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan430081 China College of Computer Science and Technology Wuhan University of Science and Technology Wuhan430081 China School of Mechanical Engineering Hubei Engineering University Xiaogan432000 China

ISBN: (纸本)9789819607761

sEMG (surface electromyography) signal control of bionic prostheses has been widely studied over the past few years. In particular, sparse sEMG signals are rapidly developing in the field of gesture recognition for their convenience, noninvasiveness, and ease of access. However, compared with high-density EMG signals, sparse EMG signals lack rich feature information, which in turn affects gesture recognition accuracy. In order to reduce the loss of feature information of sparse EMG signals in the spatio-temporal dimension, this paper proposes a hybrid neural network Res-LSTM combining residual network and long short-term memory network. The ordinary convolutional blocks in the CNN network are replaced with residual blocks, and the final fully connected layer is removed and a constant mapping layer is added to adequate extraction of spatial feature information of the data. The Res layer’s output is utilized as the input for the long and short-term memory (LSTM) network, which further extracts the features of the data in the temporal dimension, and finally completes the categorization output through a fully connected layer. The average accuracy of 91.11% for gesture-motion classification was verified by training on a homebrew dataset;and tested on a public dataset, NinaPro DB1, with an average accuracy of 91.03%. The experimental findings indicate that the proposed Res-LSTM network framework contributes to solving the problem of lack of feature information of sparse sEMG signals and improves the pattern recognition accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Optimization design of welding parameters of key components of car body based on finite element 5

Optimization design of welding parameters of key components ...

引用

2024 5th International Conference on Advanced Materials and intelligent Manufacturing, ICAMIM 2024

作者： Li, Lina Fa, Ping Sun, Hongchang He, Chuan Qiao, Zhiliang Department of Automobile Engineering Tianjin Transportation Technical College Tianjin China Huaiyuan County Vocational and Technical School Anhui Province Bengbu City China School of Mechanical Engineering Tianjin University of Technology and Education Tianjin China Tianjin Key Laboratory of Intelligent Robot Technology and Application Enterprises Tianjin China

The characteristics of the welding heat source, the morphology of the molten pool, the formation mechanism of the weld, and the amount of heat input have an important and direct influence on the welding quality and performance of the joint. At present, the empirical curve that depends on the experimental results or the calculation formula of statistics cannot comprehensively evaluate the impact of welding on the mechanical properties of the whole structure. Therefore, this research is based on the finite element analysis technique of Simufact Welding software and analyzes the evolution of the temperature field, stress field, and the deformation of the residual stress in the welding process, and provides a powerful tool and a lot of support for welding technology. The aim of the study is to develop an accurate numerical simulation method for the weld temperature field and a dynamic simulation analysis system for the weld stress field and deformation. 2025 Published under licence by IOP Publishing Ltd.

关键词： Residual stresses

来源：评论

学校读者我要写书评

暂无评论

Point-voxel dual transformer for LiDAR 3D object detection

引用

Optoelectronics Letters 2025年

作者： Tong Jigang Yang Fanhang Yang Sen Du Shengzhi Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot La-boratory， Tianjin University of Technology， 391 Binshui West Road Department of Electrical Engineering， Tshwane University of Technology

Deep learning for point clouds faces the challenge of their inherent unordered nature， which makes traditional CNN-like methods not directly applicable. However， due to the inherent permutation invariance， transformers provide solutions to unordered points problems faced in LiDAR-based object detection. In this paper， a two-stage LiDAR 3D object detection framework is presented， namely Point-Voxel Dual Transformer (PV-DT3D)， which is a transformer-based method. In the proposed PV-DT3D， point-voxel fusion features are used for proposal refinement. Specifically， in the PV-DT3D， keypoints are sampled from entire point cloud scene and used to encode representative scene features via a proposal-aware voxel set abstraction module. Subsequently， following the generation of proposals by the region proposal networks (RPN)， the internal encoded keypoints are fed into dual transformer encoder-decoder architecture. In 3D object detection， the proposed PV-DT3D is the first to take advantage of both pointwise transformer and channel-wise architecture to capture contextual information from the perspective of spatial and channel dimensions. Experiments conducted on the highly competitive KITTI 3D car detection leaderboard show that， the PV-DT3D achieves superior detection accuracy among state-of-the-art point-voxel-based methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aerodynamic trajectory simulation system for composite sounding equipment 24

Aerodynamic trajectory simulation system for composite sound...

引用

Proceedings of the 2024 4th International Conference on Computational Modeling, Simulation and Data Analysis

作者： Chun Hu Jinyang Li Dezhi Zheng Peng Peng MIIT Key Laboratory of Complex-field Intelligent Exploration Beijing Institute of Technology Beijing China Chongqing Caeri Robot Technology Co Chongqing China

ISBN: (纸本)9798400711831

The initial exploration of aerodynamic models in sounding rocket flight dynamics is undertaken in this study. This includes a comprehensive modeling and analysis of the probe-carrying parachute system deployed during descent, as well as an investigation into the aerodynamic model of unmanned aerial vehicles carried by airships. Using OSGEarth and QT, a visualization simulation platform is established, integrating high-definition digital Earth imagery and constructing foundational backgrounds. This effort encompasses the creation of simulation animations and basic feature designs, along with the establishment of real-time communication interfaces between platforms. Additionally, a user-friendly human-machine interface is implemented, incorporating several practical functions to enhance usability and improve human-machine interaction experiences.

关键词： Aerodynamic model

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：