检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Guangming Hu, Yunzhe Liu, Zhe Zhou, Yiyang Tomizuka, Masayoshi Zhan, Wei 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 Jiao Tong University China MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Mechanical Systems Control Laboratory University of California Berkeley United States

3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames. Thus, it is critical for the flow embeddings to capture the correct overall direction of the motion. However, previous works only search locally to determine a soft correspondence, ignoring the distant points that turn out to be the actual matching ones. In addition, the estimated correspondence is usually from the forward direction of the adjacent point clouds, and may not be consistent with the estimated correspondence acquired from the backward direction. To tackle these problems, we propose a novel all-to-all flow embedding layer with backward reliability validation during the initial scene flow estimation. Besides, we investigate and compare several design choices in key components of the 3D scene flow network, including the point similarity calculation, input elements of predictor, and predictor & refinement level design. After carefully choosing the most effective designs, we are able to present a model that achieves the state-of-the-art performance on FlyingThings3D and KITTI Scene Flow datasets. Our proposed model surpasses all existing methods by at least 38.2% on FlyingThings3D dataset and 24.7% on KITTI Scene Flow dataset for EPE3D metric. We release our codes at https://***/IRMVLab/3DFlow. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Visual SLAM based on geometric cluster matching

Visual SLAM based on geometric cluster matching

引用

2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019

作者： Tian, Chaoran Ou, Yongsheng Qu, Yangyang Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University OfChinese Academy of Sciences Beijing100049 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes OfAdvanced Technology Chinese Academy OfSciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781728137261

The approach of feature-based visual SLAM is very popular in Micro Aerial Vehicle (MAV) navigation and wheeled mobile robot (WMR) navigation. Most modern feature-based visual SLAM frameworks extract a fixed number of feature points and then match the feature points by brute force or adopt Fast Library for Approximate Nearest Neighbors (FLANN). The features' extracting and matching processes will determine the localization accuracy and mapping quality significantly. In this paper, we propose a feature matching algorithm for the robot equipped with a binocular camera, which provides accurate real-time localization performance and robustness. In our feature matching method, both the geometric relationship of image feature points and the similarity of descriptor are considered. This paper presents a visual SLAM framework based on geometric cluster matching and the effectiveness of the proposed method is verified by practical experiments. © 2019 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

A scalable system to synthesize data for natural scene text localization and recognition

A scalable system to synthesize data for natural scene text ...

引用

2019 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2019

作者： Wu, Qingtian Chen, Peng Zhou, Yimin Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong Provincial Engineering and Technology Research Center of Intelligent Unmanned System and Autonomous Environmental Perception China CAS Key Laboratory of Human-Machine-Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology China School of Information Engineering Nanchang University 330038 China

ISBN: (纸本)9781728137261

In this paper, a scalable system is proposed to synthesize data for multilingual text (Chinese and English) detection and recognition in cluttered conditions. The system can be realized by these following steps. First, in order to respect scene boundaries when overlaying synthetic text to existing images, hierarchical contour is obtained by using efficient graph-segmentation. Second, in order to paint text on top of surfaces with approximate natural effect, scene 3D geometry is estimated under a single image by using Convolutional Neural Network (CNN) based processing. Finally, in order to synthesize data more naturally, the text is printed into the picture appropriately by poisson image editing and the text color is rendered by a combination of foreground and background colors. The system can generate scene text data automatically and naturally, providing a cheap way to annotate massive images to train supervisor learning model for natural scene text detection and recognition. © 2018 IEEE

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Binocular depth estimation using convolutional neural network with siamese branches

Binocular depth estimation using convolutional neural networ...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Liu, Guodong Jiang, Guolai Xiong, Rong Ou, Yongsheng Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergic Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781728163215

Binocular depth estimation is a hot research topic in computer vision. Traditional methods need high precision camera calibration and key point matching, but the results are not ideal. In this paper, we introduce an approach of binocular depth estimation method based on deep learning. A new convolutional neural network is designed, which consists of two sub-networks. The first sub-network is a deep network with Siamese branches and 3D convolutional layer, it learns parallax and global information and generates a global depth estimation result in low resolution. The second is a fully convolutional deep network, which reconstructions the depth map to original resolution. The two sub-networks are connected by a pool pyramid. Experiments are taken on the Middlebury Stereo Dataset show that the proposed method can generate much more accurate depth image than traditional methods. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Terrain recognition and gait cycle prediction using IMU

Terrain recognition and gait cycle prediction using IMU

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Wang, Zhuo Zhang, Yu Ni, Jiangpeng Wu, Xinyu Liu, Yida Ye, Xin Chen, Chunjie Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China SZ DJI Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9781665436786

It is well known that terrain recognition and gait cycle prediction are important for powered exoskeleton. However, only a few works have focused on the concerns of complexity of the control system caused by using redundant sensors. In this paper, only two IMU sensors are applied to collect information of the angle and angular velocity of the hip joint in the situation of level-ground walking, ramp ascent, and ramp descent. Based on information acquired from these two IMU sensors, two methods are proposed to achieve terrain recognition. One method uses the angle of the hip joint when the two legs intersect as the threshold of terrain recognition. It can identify the terrain (level-ground walking, ramp ascent, ramp descent) during stable walking, but it cannot recognize the transitional terrain (from level-ground walking to ramp ascent, from ramp ascent to ramp descent, and so on) and its robustness is limited. The other method selects the angle and angular velocity of the hip joints as the eigenvector, and uses SVM for terrain recognition. The accuracy of terrain recognition is improved from 69.7% to 100% after introducing the Gaussian kernel function instead of Linear kernel function. For gait cycle prediction, Wiener one step prediction is applied in predicting the GC. Compared to actual GC, the error from predicted GC based on mean prediction is more than 8.0%, while the error from Wiener on step prediction is less than 4.35%. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Variation of sEMG with Muscle Fatigue for Lower Limb Stroke Patient During Walking

Variation of sEMG with Muscle Fatigue for Lower Limb Stroke ...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Shang, Wenze Huang, Ruisen Liao, Wei-Hsin Wu, Xinyu Gao, Fei Southern University of Science and Technology Shenzhen518005 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China The Chinese University of Hong Kong Department of Mechanical and Automation Engineering Hong Kong999077 Hong Kong

ISBN: (纸本)9781665481090

SEMG signal is widely used and explored in control strategies of powered assistive human-robot interaction systems due to its non-invasive nature and ability to estimate motion intention well. However, prolonged use of the sEMG-based systems leads to muscle fatigue, contributing to unstable sEMG signals and regarding the performance of sEMG-based control strategies. In this study, three subjects, including two healthy subjects and one stroke subject, participated in our experiment, and the time domain, frequency domain, and complex features extracted from their sEMG signals were utilized to evaluate muscle fatigue. The results indicate that sEMG from the stroke side of the stroke subject contains more non-linear and chaotic parts, and the statistical differences between different trials are more significant, indicating that stroke has a more significant impact on the stroke side of the stroke subject. This study suggests that RMS in the stroke side of stroke subjects is less than that in others, whereas FuzzyEn in the stroke side of stroke subjects is greater than that in others, indicating that stroke leads to different motion patterns and more susceptibility to muscle fatigue. © 2024 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Neural learning of stable dynamical systems based on extreme learning machine

Neural learning of stable dynamical systems based on extreme...

引用

International Conference on Information and Automation (ICIA)

作者： Jianbing Hu Zining Yang Zhiyang Wang Xinyu Wu Yongsheng Ou Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences Chinese University of Hong Kong China Key Lab of Human-Machine Intelligence-Synergy Systems Chinese Academy of Sciences

This paper presents a method based on extreme learning machine to learn motions from human demonstrations. We model a motion as an autonomous dynamical system and define sufficient conditions to ensure the global stability at the target. A detailed theoretic analysis is proposed on the constraints regarding to input and output weights which yields a globally stable reproduction of demonstrations. We solve the corresponding optimization problem using nonlinear programming and evaluate it on an available data set and a real robot. Combined with the generalization capacities of extreme learning machine, the results show that the human movement strategies within demonstrations can be generalized well.

关键词： Asymptotic stability Stability analysis Trajectory Robot kinematics Mathematical model Optimization

来源：评论

学校读者我要写书评

暂无评论

Using Thin-Film Piezoelectret to Detect Tactile and Slip Signals for Restoring Sensation of Prosthetic Hands

Using Thin-Film Piezoelectret to Detect Tactile and Slip Sig...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Peng Fang Lan Tian Yue Zheng Jianping Huang Guanglin Li Key Laboratory of Human-Machine-Intelligence Synergic System of Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Chinese Academy of Sciences Beijing Beijing CN

Most of the currently available prosthetic hands do not have a proper sensation of touching and slipping. Thus it is not easy for arm amputees to grasp objects properly only with an assistance of visual feedback. In this pilot work, a sensor based on thin-film piezoelectret was used to detect the possible tactile and slip information of a prosthetic hand. The piezoelectret sensor is flexible and is able to be bended, and therefore it could be properly mounted on the surface of prosthetic finger. Our preliminary results demonstrated that both the tactile and slip information could be acquired with the same sensor unit. For a grasp without slippage, the tactile signal was usually a single large peak, whereas the slip signal was a series of vibrations in a small range. Thus these two types of signals could be easily separated based on their different characteristics. This study suggested that by using thin-film piezoelectret sensor, a primary control with involuntary feedback might be achieved for the present prosthetic hands. More studies would be required on the detailed signal processing and control strategy for the restoration of sensation function in prosthetic hands.

关键词： Prosthetic hand Force Thumb Robot sensing systems Piezoelectric transducers Electromyography

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Optimization of a Piezoelectric Bending Beam-based Human Knee Energy Harvester

Optimization of a Piezoelectric Bending Beam-based Human Kne...

引用

IEEE International Conference on Mechatronics and Automation

作者： Haisu Liao Yidi Wang Qiuyu Shi Ruisen Huang Fei Gao Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy System

The concept of extracting energy from the human body to recharge depleted energy sources has gained significant attention. Recently, scientists have focused on harnessing biomechanical energy from the human body while walking. The aim of this study is to optimize a piezoelectric bending beam-based human knee energy harvester to enhance performance. Specifically, the shape of the bending beam (the substrate: a carbon fiber plate) is optimized to modulate the deformation, such that the average strain of the piezoelectric macro fiber composites (MFC) attached to the bending beam is improved to generate more electricity. In addition, the effects of the substrate’s thickness and the hinge base’s height for the bending beam on the output power are also analyzed. Experimental testing on a subject is conducted to validate our design and test the performance. The harvester generates an average power output of 24.55 mW when walking at 4 km/h on a treadmill. The harvester’s total weight is 278g.

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：