检索结果-内蒙古大学图书馆

SeaFree-GS: Reconstructing Underwater 3D Scenes With True Appearances

IEEE Signal Processing Letters 2025年 32卷 2114-2118页

作者： Liu, Shaohua Gao, Ning Fu, Shaowen Zhong, Xiaoqing Li, Hongjue Beihang University School of Astronautics Shenyuan Honors College Beijing100191 China Beihang University School of Astronautics Beijing100191 China Beijing Aerospace Automatic Control Institute Beijing100854 China National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing100854 China China Academy of Space Technology Beijing100094 China Beijing Key Laboratory of System Design for Reusable Launch Vehicle State Key Laboratory of High- Efficiency Reusable Aerospace Transportation Technology China

Reconstructing underwater 3D scenes with accurate appearances is crucial for numerous tasks. However, existing underwater 3D reconstruction methods often fail to restore the true scene appearance due to degradation in underwater images caused by water effects. In this letter, we propose SeaFree-GS, a novel approach leveraging 3D Gaussian Splatting (3DGS) to reconstruct underwater scenes with their true appearances. Specifically, we introduce a Degradation-Aware Dual-Color Modeling strategy, where each Gaussian is assigned an intrinsic color representing the true scene appearance and a viewpoint-dependent degraded color to incorporate water effects. For a given viewpoint, this strategy physically derives the corresponding degraded colors from the intrinsic colors to render the underwater image. To improve reconstruction accuracy, we introduce a Content-Based Loss for selective enhancement of supervision over foreground and background regions, and a Coarse-Grained Depth Loss to enforce additional geometric constraints. Experiments on three datasets demonstrate that SeaFree-GS achieves state-of-the-art performance in Underwater True Appearance Reconstruction, and also performs competitively in Underwater Novel View Synthesis. © 1994-2012 IEEE.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Large flexible structure vibration measurement based on machine vision 43

Large flexible structure vibration measurement based on mach...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhu, Yuanyuan Zhang, Haibo Ning, Zhijie Guo, Yanning Zheng, Lingxi Harbin Institute of Technology Harbin150001 China Beijing Institute of Control Engineering Beijing100000 China National Key Laboratory of Space Intelligent Control Beijing100000 China

ISBN: (纸本)9789887581581

A multi-target synchronous measurement method is proposed for the vibration measurement problem of large flexible structures. Select the appropriate system hardware according to the actual measurement requirements, and the binocular camera is used to acquire the image sequence of multiple points during the vibration process. An innovative method is proposed that combines feature point matching and Maximum Intersection over Union is proposed to achieve one-to-one mapping between multiple points. The vibration information of the flexible structure is obtained by image processing and three-dimensional coordinate calculation. Compared with the results obtained by the Optitrack motion capture system. Measures vibration with a frequency of 3Hz, the relative errors of most measurements are within 5%, which meets the requirements of most vibration measurements. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Vibration measurement

来源：评论

学校读者我要写书评

暂无评论

Effect of Free-End Torsion on the Corrosion and Mechanical Properties for Mg-3Zn-0.2Ca Alloy

引用

Acta Metallurgica Sinica(English Letters) 2025年第1期38卷 59-70页

作者： Li-Lan Gao Jiang Ma Yan-Song Tan Xiao-Hao Sun Qi-Jun Gao De-Bao Liu Chun-Qiu Zhang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical EngineeringTianjin University of TechnologyTianjin300384China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of TechnologyTianjin300384China School of Materials Science and Engineering Tianjin University of TechnologyTianjin300384China

Magnesium alloys with excellent degradability and biocompatibility are promising materials for biomedical implants,saving patients the burden of second ***,their mechanical properties and corrosion resistance are significantly below the requirements for implant *** study aims to improve the mechanical and corrosion resistance properties of Mg-3Zn-0.2Ca alloy by pre-torsion treatment,and find out the optimal shear *** rod-shaped Mg-3Zn-0.2Ca alloy specimens were pre-torsion treated at different torsion *** effect of free-end torsion on Mg-3Zn-0.2Ca alloy was characterized through microstructure analysis,mechanical testing,and corrosion ***-torsion treatment can refine grain and induce twins and dislocations in Mg-3Zn-0.2Ca *** surface hardness increases with the increase in torsion *** yield strength and ultimate strength initially increase and then decrease with increasing torsion angle,while ductility decreases with increasing torsion *** with a shear strain of 30%exhibit the highest tensile strength,reaching 284.78±10.62 MPa,with an elongation of 19.37±1.66%.Furthermore,they show a significant improvement in fatigue lives both before and after *** the stress amplitude is 120 MPa,the fatigue lives for specimens without pre-torsion treatment are 54,275 cycles and 4324 cycles before and after pre-corrosion,while they increased significantly to 92,015 cycles and 5050 cycles with the 30%shear strain,***,the 30%shear strain specimens show a significant reduction in corrosion *** conclusion,pre-torsion treatment can effectively modify the microstructure of Mg-3Zn-0.2Ca alloy,enhancing both mechanical properties and corrosion *** optimal shear strain for this improvement is 30%.This study provides a practical method to enhance the mechanical properties and corrosion resistance of Mg-3Zn-0.2Ca alloy,making it more suitable for biomedical implan

关键词： Magnesium alloy Pre-torsion Microstructure Mechanical property Corrosion resistance

来源：评论

学校读者我要写书评

暂无评论

Competitive Meta-Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1902-1904页

作者： Boxi Weng Jian Sun Gao Huang Fang Deng Gang Wang Jie Chen National Key Laboratory of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081 Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China School of Automation Tsinghua UniversityBeijing 100084China Department of Control Science and Engineering Tongji UniversityShanghai 201804 National Key Laboratory of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081China IEEE

Dear Editor,This letter is concerned with developing meta-learning models for fast,stable,and effective few-shot learning across tasks over a few training ***,deep and reinforcement learning(RL)is widely used in auton... 详细信息

关键词： robot autonomous concerned

来源：评论

学校读者我要写书评

暂无评论

A Fast Three-Dimensional Imaging Algorithm for Millimeter Wave Radar Based on FiNUFFT 4

A Fast Three-Dimensional Imaging Algorithm for Millimeter Wa...

引用

4th International Conference on Computer science, Electronic Information Engineering and intelligent control technology, CEI 2024

作者： Zeng, Letian Zhang, Sheng Zou, Yunhuai Li, Jingzhao Mao, Qi School of Intelligent Manufacturing Shunde Polytechnic Guangdong Foshan China Xi'An Institute of Space Radio Technology National Key Laboratory of Science and Technology on Space Microwave Shannxi Xi'an China

ISBN: (纸本)9798350378542

Millimeter wave radar is characterized by high penetration and low radiation, and its three-dimensional imaging capabilities enable the acquisition of richer target information. This has led to its widespread use in near-field three-dimensional imaging. Nevertheless, three-dimensional imaging necessitates the processing of a greater quantity of data, which in turn requires a higher computational efficiency. The interpolation operation involved in the commonly used frequency domain imaging algorithm is time-consuming and susceptible to interpolation errors, which ultimately degrades the imaging quality. This paper presents a fast three-dimensional imaging algorithm based on the Flatiron Institute Nonuniform fast Fourier transform (FiNUFFT). By substituting the traditional Stolt interpolation and subsequent fast Fourier transform (FFT) with FiNUFFT, the errors introduced by the interpolation operation are avoided and high-quality reconstruction is guaranteed with a notable increase in computational efficiency. A simulation experiment validates the effectiveness of the proposed algorithm. © 2024 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

A Fast X-ray Pulsar Time Delay Estimation Method Based on Bispectral Feature Points and Cross-Correlation 42

A Fast X-ray Pulsar Time Delay Estimation Method Based on Bi...

引用

42nd Chinese control Conference, CCC 2023

作者： Huang, Zhiwei Zong, Hua Xu, Qian Li, Xiaomin Beijing Aerospace Automatic Control Institute National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing100854 China

ISBN: (纸本)9789887581543

In order to improve the accuracy and real-time performance of X-ray pulsar time delay estimation over short-time observation interval, a method based on bispectral feature points and cross-correlation is proposed in this paper. Firstly, calculate the self-bispectrum of the standard pulsar profile, extract the bispectral feature points by PSO algorithm, and store it in the spacecraft. Secondly, the pulsar photons are received in real-time and get the observation profile by epoch folding. Thirdly, calculate the cross-bispectrum at the bispectral feature points, construct the objective function of time delay estimation, and solve the extremum. Finally, the pulsar time delay estimation is obtained by screening the extreme points using cross-correlation. Simulation experiments based on Insight-HXMT observations of the Crab pulsar show that, the average running time of the proposed algorithm is 41.59ms on Matlab R2017b, and the average estimation error at observation interval below 2.5s is 0.1858ms, which is better than the traditional bispectrum method and the selected bispectrum method. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Pulsars

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Detection Transformer with Multi-view Adaptive Feature Alignment in Remote Sensing Imagery 2

Cross-Domain Detection Transformer with Multi-view Adaptive ...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Wang, Shu Han, Jianhong Wang, Ying Hao, Xinyuan Luo, Zhaoyi Wang, Yupei Chen, Liang Beijing Institute of Technology National Key Laboratory for Science and Technology on Space-Born Intelligent Information Processing Beijing China Shanghai Academy of Spaceflight Technology Shanghai China

ISBN: (纸本)9798331515669

Unsupervised Domain Adaptation (UDA) techniques are crucial for remote sensing object detection, designed to address performance degradation caused by the domain gap between training and test data. These methods leverage unlabeled target domain data, thus alleviating the high costs associated with data annotation. Recent developments in Detection Transformers (DETR) have simplified the detection pipeline and attracted significant research interest. Building on this architecture, we introduce an unsupervised domain adaptation detector for remote sensing object detection. Specifically, we introduce a multi-view adaptive feature alignment module that initially captures domain-specific features in complex backgrounds by leveraging a cross-attention mechanism. Subsequently, we employ contrastive learning to enforce the aggregation of domain-specific features from various perspectives, thereby improving the accuracy of feature alignment. Moreover, we demonstrate that integrating the self-training framework into DETR-based detectors can significantly mitigate the domain gap by further utilizing unlabeled data in the target domain. We validated the effectiveness and generalizability of our method across two remote sensing cross-domain detection scenarios using four public datasets. © 2024 IEEE.

关键词： object detection remote sensing imagery Unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Improved almost blank subframe technology with cooperative interference suppression

Improved almost blank subframe technology with cooperative i...

引用

作者： Chen, Cong Long, Zixuan Nan, Fang Xiao, Luyao Zhu, Dijie Li, Xiang Liu, Ying Shao, Shihai National Key Laboratory of Science and Technology on Communications University of Electronic Science and Technology of China Chengdu China Telecom Research Institute Beijing China Glasgow College University of Electronic Science and Technology of China Chengdu China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China

Almost blank subframe (ABS) is a classic and efficient technology to cancel interference in cellular networks and could be applied in future networks such as ultra-density network. However, the existence of ABS will result in the deterioration of the communication capacity of the macro base station (BS), particularly for applications with large number of edge users. To solve this problem, an improved ABS technology with an interference cancelation scheme is proposed. For the considered scenario, the macro BS and the micro BS work in a cooperative manner, where the signal transmitted by the macro BS interferes with the communication between the micro BS and its edge terminals. At the terminal side, both the nonlinearity of the macro BS transmitter and the propagation model between the edge user and the macro BS are estimated using neural networks (NNs), which are then sent to the micro BS for interference elimination through the ABS. At the micro BS side, firstly, the nonlinearity and channel parameters from the ABS frame are used to generate a cancelation signal. Secondly, the cancelation signal is sent from the micro BS to the edge user to eliminate the disturbance from the macro BS. This enhanced technology can alleviate the disturbance for the edge user. Meanwhile, since it massively decreases the occupancy of ABS in the macro BS, the capacity of the macro cell can be improved. © 2023 John Wiley & Sons Ltd.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Infrared Duplicate Video Cleaning Method Based on Improved YOLOv7 5

Infrared Duplicate Video Cleaning Method Based on Improved Y...

引用

5th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2024

作者： Hu, Yiwen Hu, Yutong Zhang, Yong Liu, Tongyu Gong, Hua Shenyang Ligong University College of Science Shenyang China National Key Laboratory of Electromagnetic Space Security Tianjin China Liaoning Key Laboratory of Intelligent Optimization and Control for Ordnance Industry Shenyang China

ISBN: (纸本)9798350373820

Infrared video data is widely applied in military, transportation, security monitoring, and law enforcement. However, the equipment used for collecting and processing data often generates a significant amount of duplicate data that can negatively impact the quality of the infrared data. To address this issue and improve the quality of infrared data, we propose an improved YOLOv7 network in this paper. Our network, named AGT-ASPP-SimAM-YOLOv7, utilizes the adaptive grayscale transform (AGT) technique to enhance the contrast and brightness of infrared images. Additionally, we introduce the atrous spatial pyramid pooling (ASPP) module to fuse multi-scale feature information and the simple parameter-free attention module (SimAM) to dynamically assign feature weight. We also construct the SYLU infrared duplicate video dataset (SYLUIDVD), which includes complex backgrounds such as mountains, sky, and buildings. Experimental results show that the AGTASPP-SimAM-YOLOv7 network has the highest cleaning accuracy compared to VGG19, ResNet18, VGG16, and YOLOv7. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A lightweight object detection network based on YOLOv5 for SAR image 2

A lightweight object detection network based on YOLOv5 for S...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Shen, Aijia Zhao, Liangbo Xu, Fanyun Wang, Guoqing Liu, Wenchao Shen, Zimeng Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China

ISBN: (纸本)9798331515669

Remote sensing image target detection is one of the key technologies in the field of intelligent interpretation of remote sensing images, and it has significant application value in various areas, including military defense. When performing remote sensing image object detection on airborne and spaceborne platforms, the vast amount of remote sensing data processing and limited computational resources impose high real-time requirements on the object detection algorithms. This paper designs a lightweight object detection network model named YOLOv5-tiny, based on the existing deep learning network detection model YOLOv5s, and deploys it on the Jetson TX2 development board for training and testing. Experimental results show that the proposed YOLOv5-tiny model, when tested on the SAR-AIRcraft-1.0 with an input image size of 640x640, is 10 times smaller than YOLOv5s;it has a computational cost of 5.2 GFLOPs, which is 1/5 of YOLOv5s, and the processing time for a single image is reduced to half that of YOLOv5s, with only a 0.1% decrease in accuracy. © 2024 IEEE.

关键词： Object tracking

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：