检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Guangming Feng, Zhiheng Jiang, Chaokang Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China

Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point’s movement. Scene flow estimation is used in various applications such as autonomous driving fields, activity recognition, and virtual reality fields. As it is challenging to annotate scene flow with ground truth for real-world data, this leaves no real-world dataset available to provide a large amount of data with ground truth for scene flow estimation. Therefore, many works use synthesized data to pre-train their network and real-world LiDAR data to finetune. Unlike the previous unsupervised learning of scene flow in point clouds, we propose to use odometry information to assist the unsupervised learning of scene flow and use real-world LiDAR data to train our network. Supervised odometry provides more accurate shared cost volume for scene flow. In addition, the proposed network has mask-weighted warp layers to get a more accurate predicted point cloud. The warp operation means applying an estimated pose transformation or scene flow to a source point cloud to obtain a predicted point cloud and is the key to refining scene flow from coarse to fine. When performing warp operations, the points in different states use different weights for the pose transformation and scene flow transformation. We classify the states of points as static, dynamic, and occluded, where the static masks are used to divide static and dynamic points, and the occlusion masks are used to divide occluded points. The mask-weighted warp layer indicates that static masks and occlusion masks are used as weights when performing warp operations. Our designs are proved to be effective in ablation experiments. The experiment results show the promising prospect of an odometry-assisted unsupervised learning method for 3D scene flow in real-world data. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

arXiv

引用

arXiv 2022年

作者： Jiang, Chaokang Wang, Guangming Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for estimating scene flow from images have limitations, which split the holistic nature of 3D scene flow by estimating optical flow and disparity separately. Learning 3D scene flow from point clouds also faces the difficulties of the gap between synthesized and real data and the sparsity of LiDAR point clouds. In this paper, the generated dense depth map is utilized to obtain explicit 3D coordinates, which achieves direct learning of 3D scene flow from 2D images. The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space. Outliers in the generated 3D point cloud are removed by statistical methods to weaken the impact of noisy points on the 3D scene flow estimation task. Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow. The proposed method of self-supervised learning of 3D scene flow on real-world images is compared with a variety of methods for learning on the synthesized dataset and learning on LiDAR point clouds. The comparisons of multiple scene flow metrics are shown to demonstrate the effectiveness and superiority of introducing pseudo-LiDAR point cloud to scene flow estimation. © 2022, CC BY.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Weakly Aligned Feature Fusion for Multi-modal Object Detection

arXiv

引用

arXiv 2022年

作者： Zhang, Lu Liu, Zhiyong Zhu, Xiangyu Song, Zhan Yang, Xu Lei, Zhen Qiao, Hong The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100086 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China The Center for Biometrics and Security Research National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong The Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China

To achieve accurate and robust object detection in the real-world scenario, various forms of images are incorporated, such as color, thermal, depth, etc. However, multi-modal data often suffer from the position shift problem, i.e. the image pair is not strictly aligned, making one object has different positions in different modalities. For the deep learning method, this problem makes it difficult to fuse multi-modal features and puzzles the CNN training. In this paper, we propose a general multi-modal detector named Aligned Region CNN (AR-CNN) to tackle the position shift problem. Firstly, a region feature alignment module with adjacent similarity constraint is designed to consistently predict the position shift between two modalities and adaptively align the cross-modal region features. Secondly, we propose a novel RoI jitter strategy to improve the robustness to unexpected shift patterns. Thirdly, we present a new multi-modal feature fusion method, which selects the more reliable feature and suppresses the less useful one via feature re-weighting. Additionally, by locating bounding boxes in both modalities and building their relationships, we provide novel multi-modal labelling named KAIST-Paired. Extensive experiments on 2D and 3D object detection, RGB-T and RGB-D datasets demonstrate the effectiveness and robustness of our method. Copyright © 2022, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Gesture Control Method for Oral Blood Mixed Liquid Removal Robot*

Gesture Control Method for Oral Blood Mixed Liquid Removal R...

引用

WRC Symposium on advanced robotics and automation (WRC SARA)

作者： Xudong Ma Ziao Kuang Han Li Anqi Chen Changsheng Li Wenyong Liu Junchen Wang Yida David Hu Li Gao Bai-Quan Su Medical Robotics Laboratory School of Automation Beijing University of Posts and Tele-communications Beijing China School of Computer Beijing University of Posts and Tele-communications Beijing China School of Mechatronical Engineering Beijing Institute of Technology Beijing China Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry Beijing Advanced Innovation Centre for Biomedical Engineering School of Biological Science and Medical Engineering Beihang University Beijing China School of Mechanical Engineering and Automation Beihang University Beijing China Brigham and Women’s Hospital Harvard Medical School Boston MA USA Department of Periodontology National Stomatological Center Peking University School and Hospital of Stomatology & National Clinical Research Center for Oral Diseases Beijing China

All of oral surgeries are accompanied by bleeding. Manual removal of blood is carried out by a nurse and dozens of repetitive blood suction operations are implemented by the nurse during a single oral surgery. In our previous work, a robot for removal of blood-water mixed liquid is designed. However, the robot requires an initial order to autonomous removal of blood mixed liquid. In this paper, a hand gesture control method for typical operations of the robot is developed. Gesture dataset are developed at first and a deep learning neural network is trained for detection of hand gesture. The gesture control procedures for four typical operations are provided in detail. In a group of experiments, it’s demonstrated that an oral surgeon controls the robot’s motion by presenting prescribed hand gesture. The proposed method could be an alternative manner for blood mixed liquid removal.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grasping Detection Network with Uncertainty Estimation for Confidence-Driven Semi-Supervised Domain Adaptation

Grasping Detection Network with Uncertainty Estimation for C...

引用

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Haiyue Zhu Yiting Li Fengjun Bai Wenjie Chen Xiaocong Li Jun Ma Chek Sing Teo Pey Yuen Tao Wei Lin Mechatronics Group Singapore Institute of Manufacturing Technology (SIMTech) Singapore National University of Singapore Singapore Advanced Robotics Application Group Advanced Remanufacturing and Technology Centre (ARTC) Singapore School of Electrical Engineering and Automation Anhui University Hefei China

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

Data-efficient domain adaptation with only a few labelled data is desired for many robotic applications, e.g., in grasping detection, the inference skill learned from a grasping dataset is not universal enough to directly apply on various other daily/industrial applications. This paper presents an approach enabling the easy domain adaptation through a novel grasping detection network with confidence-driven semi-supervised learning, where these two components deeply interact with each other. The proposed grasping detection network specially provides a prediction uncertainty estimation mechanism by leveraging on Feature Pyramid Network (FPN), and the mean-teacher semi-supervised learning utilizes such uncertainty information to emphasizing the consistency loss only for those unlabelled data with high confidence, which we referred it as the confidence-driven mean teacher. This approach largely prevents the student model to learn the incorrect/harmful information from the consistency loss, which speeds up the learning progress and improves the model accuracy. Our results show that the proposed network can achieve high success rate on the Cornell grasping dataset, and for domain adaptation with very limited data, the confidence- driven mean teacher outperforms the original mean teacher and direct training by more than 10% in evaluation loss especially for avoiding the overfitting and model diverging.

关键词： Training Adaptation models Uncertainty Estimation Grasping Semisupervised learning Task analysis

来源：评论

学校读者我要写书评

暂无评论

Residual and Dense UNet for Under-Display Camera Restoration 16th

Residual and Dense UNet for Under-Display Camera Restoratio...

引用

Workshops held at the 16th European Conference on Computer Vision, ECCV 2020

作者： Yang, Qirui Liu, Yihao Tang, Jigang Ku, Tao Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Institute of Acoustics Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783030682378

With the rapid development of electronic products, the increasing demand for full-screen devices has become a new trend, which facilitates the investigation of Under-Display Cameras (UDC). UDC can not only bring larger display-to-body ratio but also improve the interactive experience. However, when imaging sensor is mounted behind a display, existing screen materials will cause severe image degradation due to lower light transmission rate and diffraction effects. In order to promote the research in this field, RLQ-TOD 2020 held the Image Restoration Challenge for Under-Display Camera. The challenge was composed of two tracks – 4k Transparent OLED (T-OLED) and phone Pentile OLED (P-OLED) track. In this paper, we propose a UNet-like structure with two various basic building blocks to tackle this problem. We discover that T-OLED and P-OLED have different preferences with the model structure and the input patch size during training. With the proposed model, our team won the third place in the challenge on both T-OLED and P-OLED tracks. © 2020, Springer Nature Switzerland AG.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Ultra-high field MRI compatible electrical and optical neural interface

引用

Sensors and Actuators A: Physical 2025年 393卷

作者： Yuan Zhang Song Le Aiping Wang Gege Zhan Xiaoyong Zhang Lihua Zhang Zhongxue Gan Xiaoyang Kang Laboratory for Neural Interface and Brain Computer Interface MOE Frontiers Center for Brain Science State Key Laboratory of Brain Function and Disorders Institute of AI & Robotics Institute of Meta-Medical Academy for Engineering & Technology College of Intelligent Robotics and Advanced Manufacturing Fudan University Shanghai 200433 China Yiwu Research Institute of Fudan University Yiwu City Zhejiang 322000 China

Neural electrical interfaces are important tools for local neural stimulation and recording, while magnetic resonance imaging (MRI) is one of the effective and non-invasive techniques for recording whole-brain signals. MRI-compatible neural interfaces combine two approaches to neural activity and is of great importance for the understanding of brain function. Therefore, it makes both requests on the magnetic and electronic performance of neural interfaces. Here, we developed MRI-compatible flexible neural interfaces based on the highly conductive metal film, for the first time. Our approach is significantly different from the traditional carbon materials or conductive polymers based neural interfaces in that the non-metal film have reduced conductivity compared with the highly conductive metal film. This approach addresses the challenges encountered while using traditional metal-based conductive film in the MRI environment by the magnetron co-sputtering of the noble metal Au-Pt film with the opposite susceptibility. As a result, our MRI-compatible flexible neural interfaces achieve the highest integration density of electrodes. The highly conductive metal based neural interfaces were tested to be functionable, and showed little artifacts in an ultra-high field 11.7 T MRI scanner, which provide the possibility to multimodal neural recording and stimulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Object Pose Estimation: A Comprehensive Survey

arXiv

引用

arXiv 2024年

作者： Liu, Jian Sun, Wei Yang, Hui Zeng, Zhiwen Liu, Chongpei Zheng, Jin Liu, Xingyu Rahmani, Hossein Sebe, Nicu Mian, Ajmal The National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China The School of Architecture and Art Central South University Changsha410082 China The Department of Automation Tsinghua University Beijing100084 China The School of Computing and Communications Lancaster University LA1 4YW United Kingdom The Department of Information Engineering and Computer Science University of Trento Trento38123 Italy The Department of Computer Science The University of Western Australia WA6009 Australia

Object pose estimation is a fundamental computer vision problem with broad applications in augmented reality and robotics. Over the past decade, deep learning models, due to their superior accuracy and robustness, have increasingly supplanted conventional algorithms reliant on engineered point pair features. Nevertheless, several challenges persist in contemporary methods, including their dependency on labeled training data, model compactness, robustness under challenging conditions, and their ability to generalize to novel unseen objects. A recent survey discussing the progress made on different aspects of this area, outstanding challenges, and promising future directions, is missing. To fill this gap, we discuss the recent advances in deep learning-based object pose estimation, covering all three formulations of the problem, i.e., instance-level, category-level, and unseen object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks, providing the readers with a holistic understanding of this field. Additionally, it discusses training paradigms of different domains, inference modes, application areas, evaluation metrics, and benchmark datasets, as well as reports the performance of current state-of-the-art methods on these benchmarks, thereby facilitating the readers in selecting the most suitable method for their application. Finally, the survey identifies key challenges, reviews the prevailing trends along with their pros and cons, and identifies promising directions for future research. We also keep tracing the latest works at Awesome-Object-Pose-Estimation. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Holographic MIMO Communications with Arbitrary Surface Placements: Near-Field LoS Channel Model and Capacity Limit

arXiv

引用

arXiv 2023年

作者： Gong, Tierui Wei, Li Huang, Chongwen Yang, Zhijia He, Jiguang Debbah, Mérouane Yuen, Chau School of Electrical and Electronics Engineering Nanyang Technological University Singapore639798 Singapore College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Hangzhou310027 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Technology Innovation Institute Masdar City Abu Dhabi9639 United Arab Emirates KU 6G Research Center Khalifa University of Science and Technology P O Box 127788 Abu Dhabi United Arab Emirates CentraleSupelec University Paris-Saclay Gif-sur-Yvette91192 France

Envisioned as one of the most promising technologies, holographic multiple-input multiple-output (H-MIMO) recently attracts notable research interests for its great potential in expanding wireless possibilities and achieving fundamental wireless limits. Empowered by the nearly continuous, large and energy-efficient surfaces with powerful electromagnetic (EM) wave control capabilities, H-MIMO opens up the opportunity for signal processing in a more fundamental EM-domain, paving the way for realizing holographic imaging level communications in supporting the extremely high spectral efficiency and energy efficiency in future networks. In this article, we propose a generalized EM-domain near-field channel modeling and study its capacity limit of point-to-point H-MIMO systems that equips arbitrarily placed surfaces in a line-of-sight (LoS) environment. Two effective and computational-efficient channel models are established from their integral counterpart, where one is with a sophisticated formula but showcases more accurate, and another is concise with a slight precision sacrifice. Furthermore, we unveil the capacity limit using our channel model, and derive a tight upper bound based upon an elaborately built analytical framework. Our result reveals that the capacity limit grows logarithmically with the product of transmit element area, receive element area, and the combined effects of 1/d2mn, 1/d4mn, and 1/d6mn over all transmit and receive antenna elements, where dmn indicates the distance between each transmit element n and receive element m. Particularly, 1/d6mn dominates in the near-field region whereas 1/d2mn dominates in the far-field region. Numerical evaluations validate the effectiveness of our channel models, and showcase the slight disparity between the upper bound and the exact capacity, which is beneficial for predicting practical system performance. Copyright © 2023, The Authors. All rights reserved.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Electron Irradiation Induced Crystallization of Amorphous Al 2 O 3 Films on Silicon Substrates

引用

MRS Online Proceedings Library 2020年第1期311卷 239-244页

作者： J. Liu C. J. Barbero J. W. Corbett K. Rajan H. Leary Department of Physics SUNY at Albany Albany USA Material Engineering Department NY State Center for Advanced Technology in Automation and Robotics Rensselaer Polytechnic Institute Troy USA IBM Corporation East Fishkill USA

An in situ study of electron beam irradiation induced amorphous-to-crystalline transformation of A12O3 films on silicon substrates has been carried out using transmission electron microscopy. Trigonal α-Al2O3 crystallites can be observed for electron beam dose rates larger than 10 mA/cm2. It is found that the nucleation and growth processes dominate near the Al2O3-Si interface. The possible effect of the silicon substrate on the growth of A12O3 crystallites is considered.

关键词：

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：