检索结果-内蒙古大学图书馆

Contour-texture preservation transformer for face super-resolution

NEUROCOMPUTING 2025年 626卷

作者： Wu, Ziyi Zhang, Yanduo Lu, Tao Zhao, Kanghui Wang, Jiaming Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan Peoples R China

In the field of computer vision, face super-resolution (FSR) technology is an important tool for enhancing the performance of basic tasks such as face recognition and video surveillance. However, when faced with complex face images, existing FSR methods often rely on the Transformer model to improve image quality through its powerful global modeling capabilities. Yet, they tend to be slightly insufficient in local feature extraction due to a lack of adequate local detail capture capabilities. To alleviate these problems, we propose a novel contour- texture preservation Transformer (CTP) method for FSR. This method consists of two key components: the multi-scale attention enhancement block (MSAEB), which captures and fuses image features of different scales to improve the detail level of feature representation, and provides high-quality input for the contour-texture Transformer enhancement block (CTTEB). Additionally, CTTEB integrates convolution operations to enhance local feature extraction and improve feature expression. The feed-forward network (FFN) we introduced ensures the full fusion of global and local information. By combining MSAEB and CTTEB into a residual progressive attention group (RPAG), the network gradually extracts and fuses multi-scale features, ultimately achieving dual preservation of contour structure and texture details. Experiments show that our method achieves the best results on LFW, FFHQ, CelebA, and Helen, with a 0.32 dB increase in PSNR, a 0.0126 increase in SSIM, and a 0.0056 increase in FSIM over the second-best model. Experiments on real-world datasets SCface and Chokepoint confirm that the CTP method excels in both FSR reconstruction and face recognition, verifying its effectiveness.

关键词： Face super-resolution Contour structure Texture details Face recognition

来源：评论

学校读者我要写书评

暂无评论

RO-BEV: Towards Robust BEV Feature Enhancement for Surround-View Instance Prediction

引用

ELECTRONICS LETTERS 2025年第1期61卷

作者： Yang, Zhi Lu, Tao Wang, Jiaming Lang, Xiujuan Fu, Shichang Han, Jifeng Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan Peoples R China

The most existing instance prediction methods often lack practical understanding and enhancement of bird's-eye view (BEV) spatial-temporal features, particularly distant features. To alleviate the above problems, we propose a robust BEV feature enhancement network (RO-BEV). The proposed RO-BEV includes two major components: the novel adaptive linearly increasing dividing (ALID) strategy and the hierarchical cross-scale fusion (HCSF) module. Specifically, the ALID strategy can mitigate instance loss caused by insufficient features by providing a linearly increasing 3D representation to build a robust BEV feature. Then, the proposed HCSF module enhances spatial-temporal BEV features in the latent space to predict vehicle instances by sampling from feature distributions at different scales and timestamps. Experimental results on the nuScenes dataset show that our RO-BEV outperforms existing state-of-the-art methods.

关键词： autonomous driving Bird's-eye view computer vision image processing instance prediction

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of a Lightweight, Ligaments-Inspired Knee Exoskeleton for Walking Assistance

引用

IEEE robotICS AND AUTOMATION LETTERS 2024年第10期9卷 8491-8498页

作者： Liu, Zhaoyuan Han, Jiaqi Han, Jianda Zhang, Juanjuan Nankai Univ Inst Robot & Automat Informat Syst Tianjin Key Lab Intelligent Robot Tianjin 300350 Peoples R China

With proper assistance, knee exoskeletons can benefit humans with impaired leg function. Prior studies found that misalignment between the knee and the exoskeleton may cause harm and undermine assistance performance. Self-aligning mechanisms can reduce misalignment but implementing them with a simple and lightweight design remains a challenge. In this letter, we designed a lightweight (740 g) knee exoskeleton that can provide assistive torque for knee extension and flexion during walking. A compact elastic limiter was proposed to reduce misalignment using an integrated shock-absorbing slider. Drawing inspiration from the cruciate ligaments, springs were equipped to reduce the nonlinearities in the alignment process. With selected spring stiffness, preliminary pressure measurements between the frames and the human body showed the exoskeleton can reduce undesired interaction forces by 50.9% during walking assistance. Preliminary experimental results demonstrated the exoskeleton can achieve high torque control performance and reduce quadriceps activities during multiple gaits. For example, the activities of the rectus femoris, vastus medialis, and vastus lateralis were reduced by an average of 23.8%, 44.0%, and 34.0%, respectively during 8(degrees) uphill walking. The initial findings indicated the system's ability to provide effective gait assistance and made it promising for improving patients' mobility.

关键词： Exoskeletons Knee Torque Legged locomotion Thigh Springs Cables Prosthetics and exoskeletons physical human-robot interaction wearable robotics

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of a Bilateral Mobile Ankle Exoskeleton With High-Efficiency Actuation

引用

IEEE robotICS AND AUTOMATION LETTERS 2024年第6期9卷 5528-5535页

作者： Chen, Jianyu Ding, Jianquan Han, Jianda Zhang, Juanjuan Nankai Univ Inst Robot & Automat Informat Syst Tianjin Key Lab Intelligent Robot Tianjin 300350 Peoples R China

Lower-limb exoskeletons can improve human mobility and endurance, especially for people with leg impairments. To minimize metabolic penalty and maximize assistance capacity, the design of the mobile exoskeleton needs to compromise between the system weight and actuation power. In the paper, we developed a lightweight high-torque mobile bilateral ankle exoskeleton with compliant end-effectors and a high-efficiency actuation. The system can provide 80 Nm assistive torques for both ankles with 3.4 kg entire exoskeleton weight by actuators' parallel connection and cooperative operation. Developed embedded hardware implemented a real-time torque controller comprising the damping-injected feedback control, model-based feedforward compensation, and iterative learning, achieving more than 10 Hz gain-limited closed-loop bandwidths and less than 2% torque tracking error. Preliminary physiological experiments demonstrated the exoskeleton's ability to reduce soleus muscle activities by over 50% at different walking speeds. Our work proved that the lightweight exoskeleton system can provide rather large torque assistance with fairly good bandwidth and tracking accuracy, promising to promote more exoskeleton applications in real life and rehabilitation.

关键词： Wearable robotics prosthetics and exoskeletons rehabilitation robotics

来源：评论

学校读者我要写书评

暂无评论

Action quality assessment via moment aware network

引用

EVOLVING SYSTEMS 2025年第2期16卷 1-10页

作者： Han, Jifeng Zhang, Yanduo Lu, Tao Wang, Jiaming Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan Peoples R China

Recent action quality assessment methods attempt to decompose the entire video into sub-actions of the same level, which still suffers from information redundancy and lacks certain interpretability. Through studying and analysing the evaluation rules of relevant sports events, we assume that certain critical moments in the actions will significantly impact the assessment of the entire action, if the weight of these critical moments in the evaluation process can be increased, then the results can be more accurate and more persuasive. To validate this idea, we propose a moment-aware approach for action quality assessment, a novel moment-aware module is used to explore the key moments in action globally and locally to obtain more reliable evaluation results. Extensive experiments have shown that our module captures key moments that are close to the focus of human referees, and our method has also achieved favorable results on multiple public AQA benchmarks, the Spearman's rank correlation reached 0.9360 on FineDiving dataset and 0.8797 on AQA-7 dataset.

关键词： Action Quality Assessment Fine-Grained Action Analyse Temporal Pattern of Sports

来源：评论

学校读者我要写书评

暂无评论

Interfacial Microstructure and Mechanical Properties of TiC-Ni Cermet Joint Brazed with Ag-Cu28 Alloy

引用

JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE 2025年 1-10页

作者： Zheng, Qingze Lei, Min Liu, Haichun Wei, Zixiong Li, Yulong Nanchang Univ Sch Adv Mfg Jiangxi Key Lab Intelligent Robot Nanchang 330031 Peoples R China

A surface Ni/Cu coating was applied to the TiC-Ni cermet using the resistive evaporation method. Subsequently, the coated cermet was joined to itself by vacuum brazing using the Ag-Cu28 brazing alloy. The study investigated the formation mechanism of the joints and the impacts of heating temperature and holding time on the joint's interfacial microstructure and mechanical properties. The results showed that during the heat treatment, the atoms within the Ni/Cu coating interdiffused, forming a continuous (Cu, Ni) layer adjacent to the cermet interface, which could promote the wettability of the liquid alloy and increase the shear strength of joints. The typical microstructure of the joints was TiC-Ni/(Cu, Ni)/Ag(s,s) + Cu(s,s)/(Cu, Ni)/TiC-Ni. Meanwhile, the joint shear strength achieved a maximum value of 146 MPa with a heating temperature of 800 degrees C for 10 min. And the joint fracture occurred in the interfacial region between the base material and the (Cu, Ni) reaction layer. The reaction layer became discontinuous with an increase in temperature or time. With increasing temperature, the shear strength tended to increase first and then decrease. With the extension of time, the shear strength gradually decreased.

关键词： brazing coating interfacial microstructure mechanical properties TiC-Ni cermet

来源：评论

学校读者我要写书评

暂无评论

MPOC-SLAM: An RGB-D SLAM System With Motion Probability and Object Category in High Dynamic Environments

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2025年第2期30卷 1061-1071页

作者： Wu, Songyang Zhang, Xuebo Zhang, Shiyong Song, Zhixing Wang, Runhua Yuan, Jing Nankai Univ Inst PLXSPACE Robot & Automat Informat Syst Coll Artificial Intelligence Tianjin Key Lab Intelligent Robot Tianjin 300350 Peoples R China

The performance of simultaneous localization and mapping (SLAM) is significantly impacted by dynamic objects. Existing dynamic SLAM methods still suffer from some major issues, such as insufficient use of semantic information, losing track when dynamic objects occupy the field of view, and inability to achieve real-time processing. In this article, we present SLAM with motion probability and object category (MPOC-SLAM), an RGB-D SLAM system capable of high-performance, real-time work in high dynamic environments. Considering intensive semantic information, our method introduces the concepts of motion probability (MP) and object category (OC), and tightly integrates them within the whole SLAM system. First, a priority feature extraction strategy is proposed based on MP, and then a dual-constraint feature matching method is designed with the adaptive probability threshold and category consistency. Both methods reduce the influence of dynamic objects in the extraction and association process. Second, to speed up the process of calculating reprojection errors, a semantic-guided geometric method with the partitioning hypothetico-deductive method is presented. The semantic-guided geometric method and instance segmentation are then fused through the variance weighted fusion with their confidences. Finally, as a more important part of SLAM, dynamic-aware weights are added to the original pose optimization, which assigns larger weights to static feature points and map points to reduce their alteration during optimization. We perform evaluations on the TUM public dataset and real-world environments. Compared with ORB-SLAM2, the percentage reduction of root mean square error of absolute trajectory error is as high as 98.72%. Results show that MPOC-SLAM realizes a significant improvement in accuracy as well as a more robust and real-time performance compared with other state-of-the-art dynamic SLAM methods.

关键词： Dynamic environments instance segmentation motion probability (MP) object category (OC) visual simultaneous localization and mapping (SLAM)

来源：评论

学校读者我要写书评

暂无评论

A four-beam piezoelectric transducer for energy harvesting and tissue hardness detection

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2025年 224卷

作者： Zhang, Jiantao Cong, Xingang Yu, Xiangfu Luo, Yi Li, Yanlong Shanghai Univ Sch Mechatron Engn & Automat Shanghai Key Lab Intelligent Mfg & Robot Shanghai Peoples R China

This paper develops a piezoelectric device that can be used for both vibration energy harvesting and soft tissue hardness detection. The piezoelectric transducer allows for simultaneous energy harvesting and hardness testing. When the piezoelectric transducer is used as an energy harvester, the four-beam piezoelectric vibration energy harvester has a good voltage output when the angle alpha between each beam of the harvester and the base plane is 0 degrees. The output power is maximum when the external load resistance is 100 k Omega. When the piezoelectric transducer is used for hardness detection, the feasibility of the hardness measurement scheme is verified by simulation analysis. By simulating the results of contact materials with different hardness levels, a calibration curve for the sensor's modal frequency and the elastic modulus of the tested object was fitted. Finally, a prototype four-beam piezoelectric sensor for energy harvesting and tissue hardness detection was fabricated. An experimental platform for vibration energy harvesting and soft tissue hardness detection was developed and different experiments were conducted. When the piezoelectric transducer is used as an energy harvester, the experimental results of the output characteristic change curve are basically consistent with the simulation results. The maximum rms output voltage of the harvester is about 423 mV and the maximum output power is about 1.79 mu W. When piezoelectric sensors are used as hardness detection sensors, it has high accuracy within the range of 0 similar to 800 kPa. The sensor can effectively detect the location of hard objects within soft samples and identify the hardness of the tested samples.

关键词： Piezoelectric Energy harvester Tactile sensor Hardness detection Theoretical model Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning-Based Automated Morphology Analysis With Atomic Force Microscopy

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2024年第4期21卷 7662-7673页

作者： Chang, Yingao Liu, Zhiang Wu, Yinan Fang, Yongchun Nankai Univ Inst Robot & Automat Informat Syst Coll Artificial Intelligence Tianjin Key Lab Intelligent Robot Tianjin 300350 Peoples R China

Morphology analysis based on atomic force microscopy (AFM) imaging contributes to understanding the characteristics of specimens more deeply. The preliminary and crucial step of implementing morphology analysis is to precisely segment the target area from the complex background. In this study, an automated AFM image segmentation strategy based on a well-designed U-shaped neural network is proposed to achieve accurate and robust segmentation for AFM images of different samples, thus realizing morphology analysis in micro-nano scale. Specifically, the centralized information interaction strategy cooperated with a two-path attention module is introduced to realize efficient cross-scale information interaction, which can fundamentally avoid the negative effects induced by spatial interpolation. Besides, the global information flows are adopted to guide the global information extracted by atrous spatial pyramid pooling to each level of the top-down pathway, which ensures that the high-level semantic information is not diluted during the top-down transmission process, thus locating the target area more precisely. Moreover, an AFM image dataset is constructed to train the network, which will be available online for free to facilitate other data-based AFM research. The segmentation results demonstrate that the proposed strategy has better performance on multiple AFM images compared with traditional Otsu method, fully convolutional network and U-Net. The application of the proposed method is carried out to exhibit the effectiveness in automated morphology analysis. Note to Practitioners-Despite the growing demand of AFM-based morphology analysis in many fields, the automated analysis is still lacking limited by accuracy and robustness of AFM image segmentation. Since manual segmentation, sometimes tedious and time-consuming, heavily depends on the personal judgment, it is thus necessary to develop automated segmentation methods. Although traditional automated segmentation al

关键词： Atomic force microscopy morphology analysis image segmentation deep learning U-shaped structure

来源：评论

学校读者我要写书评

暂无评论

A percussion-type piezoelectric vibration energy harvester

引用

MECHANICS BASED DESIGN OF STRUCTURES AND MACHINES 2025年

作者： Zhang, Jiantao Li, Yingjie Ning, Yiwen Yu, Xiangfu Shanghai Univ Sch Mechatron Engn & Automat Shanghai Key Lab Intelligent Mfg & Robot Shanghai Peoples R China

Nonlinear piezoelectric energy harvesters utilize actively designed structural dynamics to introduce nonlinear restoring forces, which enable large-amplitude oscillations over a low-frequency broadband range. This approach can enhance the efficiency of ambient vibrational energy harvesting under specific excitation conditions, compared to traditional linear systems. In this study, a novel percussive piezoelectric vibration energy harvester is developed, which, due to its symmetric cantilever beam structure, generates a knocking force under external excitation causing the harvester to switch between two states. The electromechanical coupling model of the percussive piezoelectric vibration energy harvester is established. Numerical simulations are performed to analyze the effects of different design parameters on its output performance. Three configurations of harvester prototypes are fabricated and tested. When the excitation frequency is 12 Hz and the axial compression distance of the PVDF beam is 0.2 mm, the prototype 1 achieves the maximum RMS output voltage of 3.61 V. When the excitation frequency is 12 Hz, the axial compression distance of the PVDF beam is 0.2 mm, and the load resistance is 0.2 M Omega, the maximum output power of prototype 1 reaches 32.7 mu W. The validity of the proposed model is validated by comparing simulation results with experimental data. In addition, the experimental results of the three prototypes show that the structural parameters of the harvester can be effectively designed based on the vibration characteristics of the environmental vibration source.

关键词： Piezoelectric energy harvester electromechanical coupling model percussion response numerical simulations nonlinear vibrations

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：