检索结果-内蒙古大学图书馆

Wavelet Transform-Based High-Definition Map Construction From a Panoramic Camera

Journal of Shanghai Jiaotong university(science) 2021年第5期26卷 569-576页

作者： ZHUANG Hanyang ZHOU Xuejun WANG Chunxiang QIAN Yuhan University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong UniversityShanghai 200240China Guangxi Key Laboratory of Automobile Components and Vehicle Technology Guangxi University of Science and TechnologyLiuzhou 545006GuangxiChina Noblelift Intelligent Equipment Co. Ltd.Huzhou 313100ZhejiangChina Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai 200240China School of Mechanical Engineering Shanghai Jiao Tong UniversityShanghai 200240China

High-definition(HD)maps are key components that provide rich topologic and semantic information for decision-making in vehicle autonomous driving systems.A complete ground orthophoto is usually used as the base image to construct the HD *** ground orthophoto is obtained through inverse perspective transformation and image *** the image mosaicing,multiple consecutive orthophotos are stitched together using pose information and image *** this study,wavelet transform is introduced to the image mosaicing process to alleviate the information loss caused by image *** the orthophoto wavelet transform,high-frequency and low-frequency components are fused using different strategies to form a complete base image with clearer local *** results show that the accuracy of the orthophotos generated using this method is improved.

关键词： high-definition(HD)map wavelet transform image registration panorama

来源：评论

学校读者我要写书评

暂无评论

Real-time and ultrafast optical pulse quantization based on slicing the supercontinuum

引用

Chinese Optics Letters 2021年第8期19卷 69-74页

作者： Ya Guo Qiang Cai Zhiwei Jia Bingjie Xu Zhensen Gao Qianwu Zhang Ruonan Zhang Adonis Bogris K.Alan Shore Yuncai Wang Pu Li Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of EducationTaiyuan University of TechnologyTaiyuan 030024China School of Information Engineering Guangdong University of TechnologyGuangzhou 510006China Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai UniversityShanghai 200444China School of Electronics and Information Northwestern Polytechnical UniversityXi’an 710072China Science and Technology on Communication Security Laboratory Institute of Southwestern CommunicationChengdu 610041China Department of Informatics and Computer Engineering University of West AtticaAthens 12243Greece School of Electronic Engineering Bangor UniversityWales LL571UTUnited Kingdom

All-optical analog-to-digital conversion is a paramount issue in modern science. How to implement real-time and ultrafast quantization to optical pulses with different intensities in an all-optical domain is a central problem. Here, we report a realtime demonstration of an all-optical quantization scheme based on slicing the supercontinuum in a nonlinear fiber. In comparison with previous schemes through off-line analysis of the power of different optical spectral components in the supercontinuum, this, to the best of our knowledge, is the first demonstration of such functionality online in the time ***, the extinction ratio among the quantized outputs can exceed 10 d B, which further confirms the feasibility of the proposed quantization scheme. The current 3 bit resolution in the proof-of-principle experiment is limited by the current experimental condition, but it can be expected to be greatly enhanced through improving both the spectral width of the generated supercontinuum and the number of filtering channels used.

关键词： all-optical analog-to-digital conversion photonic quantization all-optical signal processing supercontinuum generation

来源：评论

学校读者我要写书评

暂无评论

VHS to HDTV video translation using multi-task adversarial learning

arXiv

引用

arXiv 2021年

作者： Luo, Hongming Liao, Guangsen Hou, Xianxu Liu, Bozhi Zhou, Fei Qiu, Guoping College of Electronics and Information Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Nottingham Nottingham United Kingdom

There are large amount of valuable video archives in Video Home system (VHS) format. However, due to the analog nature, their quality is often poor. Compared to High-definition television (HDTV), VHS video not only has a dull color appearance but also has a lower resolution and often appears blurry. In this paper, we focus on the problem of translating VHS video to HDTV video and have developed a solution based on a novel unsupervised multi-task adversarial learning model. Inspired by the success of generative adversarial network (GAN) and CycleGAN, we employ cycle consistency loss, adversarial loss and perceptual loss together to learn a translation model. An important innovation of our work is the incorporation of super-resolution model and color transfer model that can solve unsupervised multi-task problem. To our knowledge, this is the first work that dedicated to the study of the relation between VHS and HDTV and the first computational solution to translate VHS to HDTV. We present experimental results to demonstrate the effectiveness of our solution qualitatively and quantitatively. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Sensor-less Complex system Control of PMSM Based on Improved SMO

Sensor-less Complex System Control of PMSM Based on Improved...

引用

作者： Yingjie Xiong Anna Wang Tao Zhang College Of Information Science and Engineering Northeastern University Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences School of Electrical Engineering Dalian University of Technology

The sensor-less control system of PMSM is complicated,and it is of great significance to carry out accurate mathematical modeling and simulation *** is small in size,high in efficiency,and low in noise,so it is very popular in AC motor *** have been widely used in various electrical appliances such as machine tools,robots,and household *** order to reduce the high-frequency chatter of the sensor-less control strategy of permanent magnet synchronous motors,a sensor-less control method based on improved SMO is *** back-EMF component in the static coordinate system is obtained through the *** backEMF component undergoes closed-loop feedback to eliminate the high-frequency *** back-EMF component is calculated by an improved PLL to obtain the position and speed of the rotor to improve system *** the end of the article,the feasibility is proved by comparing it with the simulation of conventional SMO-PLL.

关键词： PMSM SMO with closed-loop feed back improved PLL

来源：评论

学校读者我要写书评

暂无评论

Stereo Refinement Based on Gradient Domain Guided Filtering

Stereo Refinement Based on Gradient Domain Guided Filtering

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Jie Li Bin Chen Shiqian Wu Jun Peng Institute of Robotics and Intelligent Systems School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China School of Intelligent Technology and Engineering Chongqing University of Science and Technology Chongqing University of Technology Chongqing China

ISBN: (数字)9781728151694

ISBN: (纸本)9781728151700

The weighted median filtering with bilateral weights is currently a popular solution for disparity refinement in stereo vision, but computational complexity is an issue. In this paper, a linear disparity refinement approach based on the gradient domain guided image filtering (GDGIF) is proposed. The advantage of the proposed method is that the weights are adaptive to image structure. As such, the proposed method can remove errors in small regions, similar to salt-and-pepper noise, and large areas while edges are well preserved. Experimental results show that the proposed method can improve accuracy of disparity maps and the edges in disparity maps are better preserved than those by the state-of-the-art algorithms. Especially, the proposed disparity refinement is more efficient.

关键词： Industrial electronics Matched filters Filtering Image edge detection Venus Image filtering Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Single Image Brightening via Multi-Scale Exposure Fusion with Hybrid Learning

arXiv

引用

arXiv 2020年

作者： Zheng, Chaobing Li, Zhengguo Yang, Yi Wu, Shiqian Institute of Robotics and Intelligent Systems School of Information Science and Engineering Wuhan University of Science and Technology Wuhan430081 China Institute for Infocomm Research 138632 Singapore

A small ISO and a small exposure time are usually used to capture an image in back- or low-light condition which results in an image with negligible motion blur and small noise but looks dark. In this paper, a single image brightening algorithm is introduced to brighten such an image. The proposed algorithm includes a unique hybrid learning framework to generate two virtual images with large exposure times. The virtual images are first generated via intensity mapping functions (IMFs) which are computed using camera response functions (CRFs) and this is a model-driven approach. Both the virtual images are then enhanced by using a data-driven approach, i.e. a residual convolutional neural network to approach the ground truth images. The model-driven approach and the data-driven one compensate each other in the proposed hybrid learning framework. The final brightened image is obtained by fusing the original image and two virtual images via a multi-scale exposure fusion algorithm with properly defined weights. Experimental results show that the proposed brightening algorithm outperforms existing algorithms in terms of MEF-SSIM metric. Copyright © 2020, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

An MR Safe Rotary Encoder Based on Eccentric Sheave and FBG Sensors

An MR Safe Rotary Encoder Based on Eccentric Sheave and FBG ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Shaoping Huang Anzhu Gao Zicong Wu Chuqian Lou Yanjun Wang Guang-Zhong Yang The Institute of Medical Robotics and School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China Shanghai Jiao Tong University The Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China The Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China The Imperial College London and Empa-Swiss Federal Laboratories for Materials Science and Technology

MRI-guided robotic systems are emerging platforms for minimally invasive intervention because of high positioning accuracy and excellent tissue contrast. MR safe encoders are critical components for closed-loop robotic control. This paper develops an MR safe absolute rotary encoder based on eccentric sheave and FBG sensors. The eccentric sheave transforms the rotational motion of the shaft to the bending deflection of the beam on which FBG sensors are integrated. A model is built by establishing the relationship of the kinematics of the sheave, the mechanical properties of the beam with unknown length, and the strain model of two Fiber Bragg Grating (FBG) sensors. A Pseudo-Rigid Body (PRB) 3R model is used to solve a set of constrained equations for accurate rotary encoding. A prototype is built to calibrate the parameters and validate the accuracy of the encoder and its MR compatibility. Results show that the maximum angular error is 1.6°, and the RMS error is 0.46°. MRI shows that no noticeable artifacts are observed, and the Signal to Noise Ratio (SNR) is not affected. The results demonstrate the potential of the proposed method for it to be integrated with MR safe robots with easy fabrication, compact structures, and continuous measurement.

关键词： Mechanical sensors Shafts Analytical models Kinematics Transforms Fiber gratings Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Mechanics of soft-body rolling motion without external torque

arXiv

引用

arXiv 2024年

作者： Liang, Xudong Ding, Yimiao Yuan, Zihao Jiang, Junqi Xie, Zongling Fei, Peng Sun, Yixuan Gu, Guoying Zhong, Zheng Chen, Feifei Si, Guangwei Gong, Zhefeng School of Science Harbin Institute of Technology Shenzhen518055 China Department of Neurology The Fourth Hospital and School of Brain Science and Brain Medicine Zhejiang University School of Medicine Hangzhou310058 China Liangzhu Laboratory MOE Frontier Science Center for Brain Science and Brain-Machine Integration State Key Laboratory of Brain-Machine Intelligence Zhejiang University 1369 West Wenyi Road Hangzhou311121 China NHC and CAMS Key Laboratory of Medical Neurobiology Zhejiang University Hangzhou310058 China State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University Shanghai200240 China Robotics Institute School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China State Key Laboratory of Brain and Cognitive Science Institute of Biophysics Chinese Academy of Sciences 15 Datun Road Beijing100101 China University of Chinese Academy of Sciences 19A Yuquan Road Beijing100049 China Huazhong University of Science and Technology Optical and Electronic Information Wuhan430074 China Zhejiang Lab. Hangzhou311121 China

The Drosophila larva, a soft-body animal, can bend its body and roll efficiently to escape danger. However, contrary to common belief, this rolling motion is not driven by the imbalance of gravity and ground reaction forces. Through functional imaging and ablation experiments, we demonstrate that the sequential actuation of axial muscles within an appropriate range of angles is critical for generating rolling. We model the interplay between muscle contraction, hydrostatic skeleton deformation, and body-environment interactions, and systematically explain how sequential muscle actuation generates the rolling motion. Additionally, we constructed a pneumatic soft robot to mimic the larval rolling strategy, successfully validating our model. This mechanics model of soft-body rolling motion not only advances the study of related neural circuits, but also holds potential for applications in soft robotics. © 2024, CC BY.

关键词： Pneumatics

来源：评论

学校读者我要写书评

暂无评论

An Approach on Visual Detecting Multi-Targets in the Unstructured and Complex Scenes Based on RGB-D Images 5

An Approach on Visual Detecting Multi-Targets in the Unstruc...

引用

5th International Conference on Automation, Control and robotics engineering, CACRE 2020

作者： Tan, Qimeng Sun, Yikun Xin, Pengfei Lin, Yimin Ma, Chao Wang, Xinyu Beijing Institute of Spacecraft System Engineering Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing China Beijing Special Engineering Design and Research Institute Propellant Injection Laboratory Beijing China Beijing University of Posts Telecommunications Institute of Optical Communication Optoelectronics Beijing China Beijing Information Science and Technology University School of Instrument Science and Optoelectronic Engineering Beijing China

ISBN: (纸本)9781728198880

The technology of detecting and identifying multitarget is of significance for robotic visual navigation within the unknown, unstructured, complex scenes, whose result could be considered as important references of 3D map building and path planning for mobile robot. Traditional algorithms of target detection can be applied to 2D images without depth information generally, which is disturbed by few factors such as illumination, view and scale easily. Therefore, an approach on visual detecting multi-target of unstructured and complex scenes based on RGBD images is proposed in this article to solve the above problem, which is composed of extracting descriptor of rotation and scale invariance feature, local encoding of targets, random ferns classifier training, Hough map generation, Hough voting theoretical model and local maximum search. Experimental results have shown that the proposed approach reduce the calculation of extracting and matching local feature, improve the accuracy of object recognition and detection in unknown complex environments, be capable of well robust against few disturbing factors i.e. rotation, scale, illumination, occlusion and non-rigid body deformation. © 2020 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Position control of XY precision planar motion table based on input shaping filter

Position control of XY precision planar motion table based o...

引用

作者： HuaLiang Zhang Xu Lu DanPing Jia BingJie Zhao Tao Zhang Yang Liu HongYu Yan Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences School of Artificial Intelligence Shenyang University of Technology School of Information Science and Engineering Shenyang University of Technology

In order to solve the vibration problem of mining equipment,a Simulink simulation model of current loop,speed loop and position loop of permanent magnet synchronous motor was established to track the input position signal of the motor system.[1] At the same time,the input shaper is introduced into the motor three loop control model to study the vibration suppression effect of the input shaper.[2] The essence of the input shaper is to filter the input ***,the parameters of the input shaper need to be accurately identified and the detailed parameters of the system need to be ***,the problem that the identification accuracy of the system is not enough often makes the parameters of the shaper *** view of the problem that the system identification is not accurate,a method of adjusting and setting input shaper parameters is designed,which is not very dependent on the *** results show that the optimal parameters of the shaper can be selected by the *** with the parameters of the shaper selected according to the identification model,the vibration suppression effect is better.

关键词： system identification input shaping oscillation suppression

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：