检索结果-内蒙古大学图书馆

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

作者： Ma, Shuaizhao Liu, Fucong Wang, Haoran Tian, Baokaidi Tianjin University of Technology and Education Tianjin300222 China Tianjin Intelligent Robot Technology and Application Enterprise Key Laboratory Tianjin300222 China Co. Ltd. Tianjin300453 China

Aiming to address the problem of traditional robot joints not having the ability to perform three-degree-of-freedom omnidirectional movement, the C60 configuration robot spherical joint is designed. Dynamics analysis is performed to achieve precise control of the rotational motion of the spherical joints. Firstly, the spherical joints of a C60 configuration robot with three degrees of freedom and omnidirectional motion capability are designed. Next, the principle of motion of the spherical joint is analyzed. Then, a mathematical model is established for the coordinate position of the permanent magnet and PCB solenoid coil. The drive unit that can provide magnetic force for the target direction is selected, and the robot's spherical joint voltage control strategy is proposed for experimental validation. It is shown that the spherical joints of the C60 configuration robot have perfect symmetry, achieving a lightweight design and omnidirectional rotational motion in three degrees of freedom. A voltage control strategy for robotic spherical joints is proposed to improve response speed, reduce control complexity, and realize efficient and high-precision control. 2025 Published under licence by IOP Publishing Ltd.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic cosine 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 Laboratory， Tianjin University of Technology Department of Electrical Engineering， Tshwane University of Technology

Recently， Transformer has achieved great success in computer vision. However， it is constrained because the spatial and temporal complexity grows quadratically with the number of large points in 3D object detection applications from point clouds. Previous point-wise methods are suffering from time consumption and limited receptive fields to capture information among points. To address these limitations， we propose the cosh-attention， which reduces the computation complexity of space and time from the quadratic order to linear order with respect to the number of points. In the cosh-attention， the traditional softmax operator is replaced by non-negative ReLU activation and hyperbolic-cosine-based operator with re-weighting mechanism. Then based on the key component， cosh-attention， we present a two-stage hyperbolic cosine transformer (ChTR3D) for 3D object detection from point clouds. It refines proposals by applying cosh-attention in linear computation complexity to encode rich contextual relationships among points. Extensive experiments on the widely used KITTI dataset and Waymo Open Dataset demonstrate that， compared with vanilla attention， the cosh-attention significantly improves the inference speed with competitive performance. Experiment results show that， among two-stage state-of-the-art methods using point-level features to refine proposals， the proposed ChTR3D is the fastest one.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TSM-Based Multi-pilot Behavior Recognition Method for Ship Bridges

TSM-Based Multi-pilot Behavior Recognition Method for Ship B...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Chen, Chen Wei, Yue-Nan Hu, Song-Tao Shu, Zhong-Cheng Zhao, Xin-Zheng 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

Abnormal or non-standard operations by ship drivers are one of the major factors leading to water traffic accidents, making the development of a real-time and reliable method for detecting ship driver behavior crucial. This paper proposes a novel approach for multi-person behavior recognition based on the Temporal Shift Module (TSM) algorithm for single-target behavior detection. This algorithm integrates multi-target tracking with single-target behavior recognition methods, achieving simultaneous recognition and detection of multiple drivers within the ship’s bridge. Additionally, a dataset named "SC Action" was created for ship bridge behavior, containing data samples from various ship bridge surveillance videos, including over 1,000 video samples of routine and violation behaviors. Experimental results show that this method, while accurately tracking multiple drivers, achieved a behavior recognition accuracy of 81.72% and is capable of providing early warnings of dangerous behaviors by drivers. © 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

ShipSegNet: A Contour-Driven Instance Segmentation Method for Maritime Ship Segmentation

ShipSegNet: A Contour-Driven Instance Segmentation Method fo...

引用

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

A Knowledge-Enhanced Contrastive Learning Network for Weakly-Supervised Aspect Detection

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 506-517页

作者： Zhuoming Zheng Yi Cai Liuwu Li School of Software Engineering South China University of Technology Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou China

Aspect detection, aiming at identifying the aspects of review segments, is a fundamental task in opinion mining and aspect-based sentiment analysis. Due to the high cost and time consuming of human-annotation for massive reviews, several unsupervised and weakly-supervised methods are proposed recently. However, existing weakly-supervised models are mostly seed-driven methods based on co-occurrence of words, which suffer from lacking the ability of detecting the aspects with infrequent aspect terms and identifying Misc aspect. To tackle these problems, we leverage external knowledge to enhance the representation of aspects and segments by a weakly-supervised method. In this paper, we propose an aspect knowledge-enhanced contrastive learning (AKECL) network with two powerful knowledge-enhanced encoders for aspects and reivew segments to enhance weakly-supervised aspect detection task. Experiments in seven different domains show that AKECL outperforms the competitive baselines, and demonstrate the effectiveness of our proposed method, as well as the improvement by introducing external knowledge.

关键词： Reviews Contrastive learning Vectors Feature extraction Knowledge graphs Speech processing Sentiment analysis Knowledge engineering Hardware Touch sensitive screens

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

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：